Computer vision

Subterms

    Latest story

    113 Shares99 Views

    Researchers use large language models to help robots navigate

    by

    Someday, you may want your home robot to carry a load of dirty clothes downstairs and deposit them in the washing machine in the far-left corner of the basement. The robot will need to combine your instructions with its visual observations to determine the steps it should take to complete this task.For an AI agent, this is easier said than done. Current approaches often utilize multiple hand-crafted machine-learning models to tackle different parts of the task, which require a great deal of human effort and expertise to build. These methods, which use visual representations to directly make navigation decisions, demand massive amounts of visual data for training, which are often hard to come by.To overcome these challenges, researchers from MIT and the MIT-IBM Watson AI Lab devised a navigation method that converts visual representations into pieces of language, which are then fed into one large language model that achieves all parts of the multistep navigation task.Rather than encoding visual features from images of a robot’s surroundings as visual representations, which is computationally intensive, their method creates text captions that describe the robot’s point-of-view. A large language model uses the captions to predict the actions a robot should take to fulfill a user’s language-based instructions.Because their method utilizes purely language-based representations, they can use a large language model to efficiently generate a huge amount of synthetic training data.While this approach does not outperform techniques that use visual features, it performs well in situations that lack enough visual data for training. The researchers found that combining their language-based inputs with visual signals leads to better navigation performance.“By purely using language as the perceptual representation, ours is a more straightforward approach. Since all the inputs can be encoded as language, we can generate a human-understandable trajectory,” says Bowen Pan, an electrical engineering and computer science (EECS) graduate student and lead author of a paper on this approach.Pan’s co-authors include his advisor, Aude Oliva, director of strategic industry engagement at the MIT Schwarzman College of Computing, MIT director of the MIT-IBM Watson AI Lab, and a senior research scientist in the Computer Science and Artificial Intelligence Laboratory (CSAIL); Philip Isola, an associate professor of EECS and a member of CSAIL; senior author Yoon Kim, an assistant professor of EECS and a member of CSAIL; and others at the MIT-IBM Watson AI Lab and Dartmouth College. The research will be presented at the Conference of the North American Chapter of the Association for Computational Linguistics.Solving a vision problem with languageSince large language models are the most powerful machine-learning models available, the researchers sought to incorporate them into the complex task known as vision-and-language navigation, Pan says.But such models take text-based inputs and can’t process visual data from a robot’s camera. So, the team needed to find a way to use language instead.Their technique utilizes a simple captioning model to obtain text descriptions of a robot’s visual observations. These captions are combined with language-based instructions and fed into a large language model, which decides what navigation step the robot should take next.The large language model outputs a caption of the scene the robot should see after completing that step. This is used to update the trajectory history so the robot can keep track of where it has been.The model repeats these processes to generate a trajectory that guides the robot to its goal, one step at a time.To streamline the process, the researchers designed templates so observation information is presented to the model in a standard form — as a series of choices the robot can make based on its surroundings.For instance, a caption might say “to your 30-degree left is a door with a potted plant beside it, to your back is a small office with a desk and a computer,” etc. The model chooses whether the robot should move toward the door or the office.“One of the biggest challenges was figuring out how to encode this kind of information into language in a proper way to make the agent understand what the task is and how they should respond,” Pan says.Advantages of languageWhen they tested this approach, while it could not outperform vision-based techniques, they found that it offered several advantages.First, because text requires fewer computational resources to synthesize than complex image data, their method can be used to rapidly generate synthetic training data. In one test, they generated 10,000 synthetic trajectories based on 10 real-world, visual trajectories.The technique can also bridge the gap that can prevent an agent trained with a simulated environment from performing well in the real world. This gap often occurs because computer-generated images can appear quite different from real-world scenes due to elements like lighting or color. But language that describes a synthetic versus a real image would be much harder to tell apart, Pan says. Also, the representations their model uses are easier for a human to understand because they are written in natural language.“If the agent fails to reach its goal, we can more easily determine where it failed and why it failed. Maybe the history information is not clear enough or the observation ignores some important details,” Pan says.In addition, their method could be applied more easily to varied tasks and environments because it uses only one type of input. As long as data can be encoded as language, they can use the same model without making any modifications.But one disadvantage is that their method naturally loses some information that would be captured by vision-based models, such as depth information.However, the researchers were surprised to see that combining language-based representations with vision-based methods improves an agent’s ability to navigate.“Maybe this means that language can capture some higher-level information than cannot be captured with pure vision features,” he says.This is one area the researchers want to continue exploring. They also want to develop a navigation-oriented captioner that could boost the method’s performance. In addition, they want to probe the ability of large language models to exhibit spatial awareness and see how this could aid language-based navigation.This research is funded, in part, by the MIT-IBM Watson AI Lab. More

    More stories

    • 200 Shares159 Views

      in Data Management & Statistics

      Looking for a specific action in a video? This AI-based method can find it for you

      by

      The internet is awash in instructional videos that can teach curious viewers everything from cooking the perfect pancake to performing a life-saving Heimlich maneuver.But pinpointing when and where a particular action happens in a long video can be tedious. To streamline the process, scientists are trying to teach computers to perform this task. Ideally, a user could just describe the action they’re looking for, and an AI model would skip to its location in the video.However, teaching machine-learning models to do this usually requires a great deal of expensive video data that have been painstakingly hand-labeled.A new, more efficient approach from researchers at MIT and the MIT-IBM Watson AI Lab trains a model to perform this task, known as spatio-temporal grounding, using only videos and their automatically generated transcripts.The researchers teach a model to understand an unlabeled video in two distinct ways: by looking at small details to figure out where objects are located (spatial information) and looking at the bigger picture to understand when the action occurs (temporal information).Compared to other AI approaches, their method more accurately identifies actions in longer videos with multiple activities. Interestingly, they found that simultaneously training on spatial and temporal information makes a model better at identifying each individually.In addition to streamlining online learning and virtual training processes, this technique could also be useful in health care settings by rapidly finding key moments in videos of diagnostic procedures, for example.“We disentangle the challenge of trying to encode spatial and temporal information all at once and instead think about it like two experts working on their own, which turns out to be a more explicit way to encode the information. Our model, which combines these two separate branches, leads to the best performance,” says Brian Chen, lead author of a paper on this technique.Chen, a 2023 graduate of Columbia University who conducted this research while a visiting student at the MIT-IBM Watson AI Lab, is joined on the paper by James Glass, senior research scientist, member of the MIT-IBM Watson AI Lab, and head of the Spoken Language Systems Group in the Computer Science and Artificial Intelligence Laboratory (CSAIL); Hilde Kuehne, a member of the MIT-IBM Watson AI Lab who is also affiliated with Goethe University Frankfurt; and others at MIT, Goethe University, the MIT-IBM Watson AI Lab, and Quality Match GmbH. The research will be presented at the Conference on Computer Vision and Pattern Recognition.Global and local learningResearchers usually teach models to perform spatio-temporal grounding using videos in which humans have annotated the start and end times of particular tasks.Not only is generating these data expensive, but it can be difficult for humans to figure out exactly what to label. If the action is “cooking a pancake,” does that action start when the chef begins mixing the batter or when she pours it into the pan?“This time, the task may be about cooking, but next time, it might be about fixing a car. There are so many different domains for people to annotate. But if we can learn everything without labels, it is a more general solution,” Chen says.For their approach, the researchers use unlabeled instructional videos and accompanying text transcripts from a website like YouTube as training data. These don’t need any special preparation.They split the training process into two pieces. For one, they teach a machine-learning model to look at the entire video to understand what actions happen at certain times. This high-level information is called a global representation.For the second, they teach the model to focus on a specific region in parts of the video where action is happening. In a large kitchen, for instance, the model might only need to focus on the wooden spoon a chef is using to mix pancake batter, rather than the entire counter. This fine-grained information is called a local representation.The researchers incorporate an additional component into their framework to mitigate misalignments that occur between narration and video. Perhaps the chef talks about cooking the pancake first and performs the action later.To develop a more realistic solution, the researchers focused on uncut videos that are several minutes long. In contrast, most AI techniques train using few-second clips that someone trimmed to show only one action.A new benchmarkBut when they came to evaluate their approach, the researchers couldn’t find an effective benchmark for testing a model on these longer, uncut videos — so they created one.To build their benchmark dataset, the researchers devised a new annotation technique that works well for identifying multistep actions. They had users mark the intersection of objects, like the point where a knife edge cuts a tomato, rather than drawing a box around important objects.“This is more clearly defined and speeds up the annotation process, which reduces the human labor and cost,” Chen says.Plus, having multiple people do point annotation on the same video can better capture actions that occur over time, like the flow of milk being poured. All annotators won’t mark the exact same point in the flow of liquid.When they used this benchmark to test their approach, the researchers found that it was more accurate at pinpointing actions than other AI techniques.Their method was also better at focusing on human-object interactions. For instance, if the action is “serving a pancake,” many other approaches might focus only on key objects, like a stack of pancakes sitting on a counter. Instead, their method focuses on the actual moment when the chef flips a pancake onto a plate.Next, the researchers plan to enhance their approach so models can automatically detect when text and narration are not aligned, and switch focus from one modality to the other. They also want to extend their framework to audio data, since there are usually strong correlations between actions and the sounds objects make.“AI research has made incredible progress towards creating models like ChatGPT that understand images. But our progress on understanding video is far behind. This work represents a significant step forward in that direction,” says Kate Saenko, a professor in the Department of Computer Science at Boston University who was not involved with this work.This research is funded, in part, by the MIT-IBM Watson AI Lab. More

    • 50 Shares169 Views

      in Data Management & Statistics

      Advancing technology for aquaculture

      by

      According to the National Oceanic and Atmospheric Administration, aquaculture in the United States represents a $1.5 billion industry annually. Like land-based farming, shellfish aquaculture requires healthy seed production in order to maintain a sustainable industry. Aquaculture hatchery production of shellfish larvae — seeds — requires close monitoring to track mortality rates and assess health from the earliest stages of life. 

      Careful observation is necessary to inform production scheduling, determine effects of naturally occurring harmful bacteria, and ensure sustainable seed production. This is an essential step for shellfish hatcheries but is currently a time-consuming manual process prone to human error. 

      With funding from MIT’s Abdul Latif Jameel Water and Food Systems Lab (J-WAFS), MIT Sea Grant is working with Associate Professor Otto Cordero of the MIT Department of Civil and Environmental Engineering, Professor Taskin Padir and Research Scientist Mark Zolotas at the Northeastern University Institute for Experiential Robotics, and others at the Aquaculture Research Corporation (ARC), and the Cape Cod Commercial Fishermen’s Alliance, to advance technology for the aquaculture industry. Located on Cape Cod, ARC is a leading shellfish hatchery, farm, and wholesaler that plays a vital role in providing high-quality shellfish seed to local and regional growers.

      Two MIT students have joined the effort this semester, working with Robert Vincent, MIT Sea Grant’s assistant director of advisory services, through the Undergraduate Research Opportunities Program (UROP). 

      First-year student Unyime Usua and sophomore Santiago Borrego are using microscopy images of shellfish seed from ARC to train machine learning algorithms that will help automate the identification and counting process. The resulting user-friendly image recognition tool aims to aid aquaculturists in differentiating and counting healthy, unhealthy, and dead shellfish larvae, improving accuracy and reducing time and effort.

      Vincent explains that AI is a powerful tool for environmental science that enables researchers, industry, and resource managers to address challenges that have long been pinch points for accurate data collection, analysis, predictions, and streamlining processes. “Funding support from programs like J-WAFS enable us to tackle these problems head-on,” he says. 

      ARC faces challenges with manually quantifying larvae classes, an important step in their seed production process. “When larvae are in their growing stages they are constantly being sized and counted,” explains Cheryl James, ARC larval/juvenile production manager. “This process is critical to encourage optimal growth and strengthen the population.” 

      Developing an automated identification and counting system will help to improve this step in the production process with time and cost benefits. “This is not an easy task,” says Vincent, “but with the guidance of Dr. Zolotas at the Northeastern University Institute for Experiential Robotics and the work of the UROP students, we have made solid progress.” 

      The UROP program benefits both researchers and students. Involving MIT UROP students in developing these types of systems provides insights into AI applications that they might not have considered, providing opportunities to explore, learn, and apply themselves while contributing to solving real challenges.

      Borrego saw this project as an opportunity to apply what he’d learned in class 6.390 (Introduction to Machine Learning) to a real-world issue. “I was starting to form an idea of how computers can see images and extract information from them,” he says. “I wanted to keep exploring that.”

      Usua decided to pursue the project because of the direct industry impacts it could have. “I’m pretty interested in seeing how we can utilize machine learning to make people’s lives easier. We are using AI to help biologists make this counting and identification process easier.” While Usua wasn’t familiar with aquaculture before starting this project, she explains, “Just hearing about the hatcheries that Dr. Vincent was telling us about, it was unfortunate that not a lot of people know what’s going on and the problems that they’re facing.”

      On Cape Cod alone, aquaculture is an $18 million per year industry. But the Massachusetts Division of Marine Fisheries estimates that hatcheries are only able to meet 70–80 percent of seed demand annually, which impacts local growers and economies. Through this project, the partners aim to develop technology that will increase seed production, advance industry capabilities, and help understand and improve the hatchery microbiome.

      Borrego explains the initial challenge of having limited data to work with. “Starting out, we had to go through and label all of the data, but going through that process helped me learn a lot.” In true MIT fashion, he shares his takeaway from the project: “Try to get the best out of what you’re given with the data you have to work with. You’re going to have to adapt and change your strategies depending on what you have.”

      Usua describes her experience going through the research process, communicating in a team, and deciding what approaches to take. “Research is a difficult and long process, but there is a lot to gain from it because it teaches you to look for things on your own and find your own solutions to problems.”

      In addition to increasing seed production and reducing the human labor required in the hatchery process, the collaborators expect this project to contribute to cost savings and technology integration to support one of the most underserved industries in the United States. 

      Borrego and Usua both plan to continue their work for a second semester with MIT Sea Grant. Borrego is interested in learning more about how technology can be used to protect the environment and wildlife. Usua says she hopes to explore more projects related to aquaculture. “It seems like there’s an infinite amount of ways to tackle these issues.” More

    • 138 Shares139 Views

      in Data Management & Statistics

      AI generates high-quality images 30 times faster in a single step

      by

      In our current age of artificial intelligence, computers can generate their own “art” by way of diffusion models, iteratively adding structure to a noisy initial state until a clear image or video emerges. Diffusion models have suddenly grabbed a seat at everyone’s table: Enter a few words and experience instantaneous, dopamine-spiking dreamscapes at the intersection of reality and fantasy. Behind the scenes, it involves a complex, time-intensive process requiring numerous iterations for the algorithm to perfect the image.

      MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) researchers have introduced a new framework that simplifies the multi-step process of traditional diffusion models into a single step, addressing previous limitations. This is done through a type of teacher-student model: teaching a new computer model to mimic the behavior of more complicated, original models that generate images. The approach, known as distribution matching distillation (DMD), retains the quality of the generated images and allows for much faster generation. 

      “Our work is a novel method that accelerates current diffusion models such as Stable Diffusion and DALLE-3 by 30 times,” says Tianwei Yin, an MIT PhD student in electrical engineering and computer science, CSAIL affiliate, and the lead researcher on the DMD framework. “This advancement not only significantly reduces computational time but also retains, if not surpasses, the quality of the generated visual content. Theoretically, the approach marries the principles of generative adversarial networks (GANs) with those of diffusion models, achieving visual content generation in a single step — a stark contrast to the hundred steps of iterative refinement required by current diffusion models. It could potentially be a new generative modeling method that excels in speed and quality.”

      This single-step diffusion model could enhance design tools, enabling quicker content creation and potentially supporting advancements in drug discovery and 3D modeling, where promptness and efficacy are key.

      Distribution dreams

      DMD cleverly has two components. First, it uses a regression loss, which anchors the mapping to ensure a coarse organization of the space of images to make training more stable. Next, it uses a distribution matching loss, which ensures that the probability to generate a given image with the student model corresponds to its real-world occurrence frequency. To do this, it leverages two diffusion models that act as guides, helping the system understand the difference between real and generated images and making training the speedy one-step generator possible.

      The system achieves faster generation by training a new network to minimize the distribution divergence between its generated images and those from the training dataset used by traditional diffusion models. “Our key insight is to approximate gradients that guide the improvement of the new model using two diffusion models,” says Yin. “In this way, we distill the knowledge of the original, more complex model into the simpler, faster one, while bypassing the notorious instability and mode collapse issues in GANs.” 

      Yin and colleagues used pre-trained networks for the new student model, simplifying the process. By copying and fine-tuning parameters from the original models, the team achieved fast training convergence of the new model, which is capable of producing high-quality images with the same architectural foundation. “This enables combining with other system optimizations based on the original architecture to further accelerate the creation process,” adds Yin. 

      When put to the test against the usual methods, using a wide range of benchmarks, DMD showed consistent performance. On the popular benchmark of generating images based on specific classes on ImageNet, DMD is the first one-step diffusion technique that churns out pictures pretty much on par with those from the original, more complex models, rocking a super-close Fréchet inception distance (FID) score of just 0.3, which is impressive, since FID is all about judging the quality and diversity of generated images. Furthermore, DMD excels in industrial-scale text-to-image generation and achieves state-of-the-art one-step generation performance. There’s still a slight quality gap when tackling trickier text-to-image applications, suggesting there’s a bit of room for improvement down the line. 

      Additionally, the performance of the DMD-generated images is intrinsically linked to the capabilities of the teacher model used during the distillation process. In the current form, which uses Stable Diffusion v1.5 as the teacher model, the student inherits limitations such as rendering detailed depictions of text and small faces, suggesting that DMD-generated images could be further enhanced by more advanced teacher models. 

      “Decreasing the number of iterations has been the Holy Grail in diffusion models since their inception,” says Fredo Durand, MIT professor of electrical engineering and computer science, CSAIL principal investigator, and a lead author on the paper. “We are very excited to finally enable single-step image generation, which will dramatically reduce compute costs and accelerate the process.” 

      “Finally, a paper that successfully combines the versatility and high visual quality of diffusion models with the real-time performance of GANs,” says Alexei Efros, a professor of electrical engineering and computer science at the University of California at Berkeley who was not involved in this study. “I expect this work to open up fantastic possibilities for high-quality real-time visual editing.” 

      Yin and Durand’s fellow authors are MIT electrical engineering and computer science professor and CSAIL principal investigator William T. Freeman, as well as Adobe research scientists Michaël Gharbi SM ’15, PhD ’18; Richard Zhang; Eli Shechtman; and Taesung Park. Their work was supported, in part, by U.S. National Science Foundation grants (including one for the Institute for Artificial Intelligence and Fundamental Interactions), the Singapore Defense Science and Technology Agency, and by funding from Gwangju Institute of Science and Technology and Amazon. Their work will be presented at the Conference on Computer Vision and Pattern Recognition in June. More

    • 100 Shares129 Views

      in Data Management & Statistics

      MIT researchers remotely map crops, field by field

      by

      Crop maps help scientists and policymakers track global food supplies and estimate how they might shift with climate change and growing populations. But getting accurate maps of the types of crops that are grown from farm to farm often requires on-the-ground surveys that only a handful of countries have the resources to maintain.

      Now, MIT engineers have developed a method to quickly and accurately label and map crop types without requiring in-person assessments of every single farm. The team’s method uses a combination of Google Street View images, machine learning, and satellite data to automatically determine the crops grown throughout a region, from one fraction of an acre to the next. 

      The researchers used the technique to automatically generate the first nationwide crop map of Thailand — a smallholder country where small, independent farms make up the predominant form of agriculture. The team created a border-to-border map of Thailand’s four major crops — rice, cassava, sugarcane, and maize — and determined which of the four types was grown, at every 10 meters, and without gaps, across the entire country. The resulting map achieved an accuracy of 93 percent, which the researchers say is comparable to on-the-ground mapping efforts in high-income, big-farm countries.

      The team is applying their mapping technique to other countries such as India, where small farms sustain most of the population but the type of crops grown from farm to farm has historically been poorly recorded.

      “It’s a longstanding gap in knowledge about what is grown around the world,” says Sherrie Wang, the d’Arbeloff Career Development Assistant Professor in MIT’s Department of Mechanical Engineering, and the Institute for Data, Systems, and Society (IDSS). “The final goal is to understand agricultural outcomes like yield, and how to farm more sustainably. One of the key preliminary steps is to map what is even being grown — the more granularly you can map, the more questions you can answer.”

      Wang, along with MIT graduate student Jordi Laguarta Soler and Thomas Friedel of the agtech company PEAT GmbH, will present a paper detailing their mapping method later this month at the AAAI Conference on Artificial Intelligence.

      Ground truth

      Smallholder farms are often run by a single family or farmer, who subsist on the crops and livestock that they raise. It’s estimated that smallholder farms support two-thirds of the world’s rural population and produce 80 percent of the world’s food. Keeping tabs on what is grown and where is essential to tracking and forecasting food supplies around the world. But the majority of these small farms are in low to middle-income countries, where few resources are devoted to keeping track of individual farms’ crop types and yields.

      Crop mapping efforts are mainly carried out in high-income regions such as the United States and Europe, where government agricultural agencies oversee crop surveys and send assessors to farms to label crops from field to field. These “ground truth” labels are then fed into machine-learning models that make connections between the ground labels of actual crops and satellite signals of the same fields. They then label and map wider swaths of farmland that assessors don’t cover but that satellites automatically do.

      “What’s lacking in low- and middle-income countries is this ground label that we can associate with satellite signals,” Laguarta Soler says. “Getting these ground truths to train a model in the first place has been limited in most of the world.”

      The team realized that, while many developing countries do not have the resources to maintain crop surveys, they could potentially use another source of ground data: roadside imagery, captured by services such as Google Street View and Mapillary, which send cars throughout a region to take continuous 360-degree images with dashcams and rooftop cameras.

      In recent years, such services have been able to access low- and middle-income countries. While the goal of these services is not specifically to capture images of crops, the MIT team saw that they could search the roadside images to identify crops.

      Cropped image

      In their new study, the researchers worked with Google Street View (GSV) images taken throughout Thailand — a country that the service has recently imaged fairly thoroughly, and which consists predominantly of smallholder farms.

      Starting with over 200,000 GSV images randomly sampled across Thailand, the team filtered out images that depicted buildings, trees, and general vegetation. About 81,000 images were crop-related. They set aside 2,000 of these, which they sent to an agronomist, who determined and labeled each crop type by eye. They then trained a convolutional neural network to automatically generate crop labels for the other 79,000 images, using various training methods, including iNaturalist — a web-based crowdsourced  biodiversity database, and GPT-4V, a “multimodal large language model” that enables a user to input an image and ask the model to identify what the image is depicting. For each of the 81,000 images, the model generated a label of one of four crops that the image was likely depicting — rice, maize, sugarcane, or cassava.

      The researchers then paired each labeled image with the corresponding satellite data taken of the same location throughout a single growing season. These satellite data include measurements across multiple wavelengths, such as a location’s greenness and its reflectivity (which can be a sign of water). 

      “Each type of crop has a certain signature across these different bands, which changes throughout a growing season,” Laguarta Soler notes.

      The team trained a second model to make associations between a location’s satellite data and its corresponding crop label. They then used this model to process satellite data taken of the rest of the country, where crop labels were not generated or available. From the associations that the model learned, it then assigned crop labels across Thailand, generating a country-wide map of crop types, at a resolution of 10 square meters.

      This first-of-its-kind crop map included locations corresponding to the 2,000 GSV images that the researchers originally set aside, that were labeled by arborists. These human-labeled images were used to validate the map’s labels, and when the team looked to see whether the map’s labels matched the expert, “gold standard” labels, it did so 93 percent of the time.

      “In the U.S., we’re also looking at over 90 percent accuracy, whereas with previous work in India, we’ve only seen 75 percent because ground labels are limited,” Wang says. “Now we can create these labels in a cheap and automated way.”

      The researchers are moving to map crops across India, where roadside images via Google Street View and other services have recently become available.

      “There are over 150 million smallholder farmers in India,” Wang says. “India is covered in agriculture, almost wall-to-wall farms, but very small farms, and historically it’s been very difficult to create maps of India because there are very sparse ground labels.”

      The team is working to generate crop maps in India, which could be used to inform policies having to do with assessing and bolstering yields, as global temperatures and populations rise.

      “What would be interesting would be to create these maps over time,” Wang says. “Then you could start to see trends, and we can try to relate those things to anything like changes in climate and policies.” More

    • 125 Shares169 Views

      in Data Management & Statistics

      Multiple AI models help robots execute complex plans more transparently

      by

      Your daily to-do list is likely pretty straightforward: wash the dishes, buy groceries, and other minutiae. It’s unlikely you wrote out “pick up the first dirty dish,” or “wash that plate with a sponge,” because each of these miniature steps within the chore feels intuitive. While we can routinely complete each step without much thought, a robot requires a complex plan that involves more detailed outlines.

      MIT’s Improbable AI Lab, a group within the Computer Science and Artificial Intelligence Laboratory (CSAIL), has offered these machines a helping hand with a new multimodal framework: Compositional Foundation Models for Hierarchical Planning (HiP), which develops detailed, feasible plans with the expertise of three different foundation models. Like OpenAI’s GPT-4, the foundation model that ChatGPT and Bing Chat were built upon, these foundation models are trained on massive quantities of data for applications like generating images, translating text, and robotics.Unlike RT2 and other multimodal models that are trained on paired vision, language, and action data, HiP uses three different foundation models each trained on different data modalities. Each foundation model captures a different part of the decision-making process and then works together when it’s time to make decisions. HiP removes the need for access to paired vision, language, and action data, which is difficult to obtain. HiP also makes the reasoning process more transparent.

      What’s considered a daily chore for a human can be a robot’s “long-horizon goal” — an overarching objective that involves completing many smaller steps first — requiring sufficient data to plan, understand, and execute objectives. While computer vision researchers have attempted to build monolithic foundation models for this problem, pairing language, visual, and action data is expensive. Instead, HiP represents a different, multimodal recipe: a trio that cheaply incorporates linguistic, physical, and environmental intelligence into a robot.

      “Foundation models do not have to be monolithic,” says NVIDIA AI researcher Jim Fan, who was not involved in the paper. “This work decomposes the complex task of embodied agent planning into three constituent models: a language reasoner, a visual world model, and an action planner. It makes a difficult decision-making problem more tractable and transparent.”The team believes that their system could help these machines accomplish household chores, such as putting away a book or placing a bowl in the dishwasher. Additionally, HiP could assist with multistep construction and manufacturing tasks, like stacking and placing different materials in specific sequences.Evaluating HiP

      The CSAIL team tested HiP’s acuity on three manipulation tasks, outperforming comparable frameworks. The system reasoned by developing intelligent plans that adapt to new information.

      First, the researchers requested that it stack different-colored blocks on each other and then place others nearby. The catch: Some of the correct colors weren’t present, so the robot had to place white blocks in a color bowl to paint them. HiP often adjusted to these changes accurately, especially compared to state-of-the-art task planning systems like Transformer BC and Action Diffuser, by adjusting its plans to stack and place each square as needed.

      Another test: arranging objects such as candy and a hammer in a brown box while ignoring other items. Some of the objects it needed to move were dirty, so HiP adjusted its plans to place them in a cleaning box, and then into the brown container. In a third demonstration, the bot was able to ignore unnecessary objects to complete kitchen sub-goals such as opening a microwave, clearing a kettle out of the way, and turning on a light. Some of the prompted steps had already been completed, so the robot adapted by skipping those directions.

      A three-pronged hierarchy

      HiP’s three-pronged planning process operates as a hierarchy, with the ability to pre-train each of its components on different sets of data, including information outside of robotics. At the bottom of that order is a large language model (LLM), which starts to ideate by capturing all the symbolic information needed and developing an abstract task plan. Applying the common sense knowledge it finds on the internet, the model breaks its objective into sub-goals. For example, “making a cup of tea” turns into “filling a pot with water,” “boiling the pot,” and the subsequent actions required.

      “All we want to do is take existing pre-trained models and have them successfully interface with each other,” says Anurag Ajay, a PhD student in the MIT Department of Electrical Engineering and Computer Science (EECS) and a CSAIL affiliate. “Instead of pushing for one model to do everything, we combine multiple ones that leverage different modalities of internet data. When used in tandem, they help with robotic decision-making and can potentially aid with tasks in homes, factories, and construction sites.”

      These models also need some form of “eyes” to understand the environment they’re operating in and correctly execute each sub-goal. The team used a large video diffusion model to augment the initial planning completed by the LLM, which collects geometric and physical information about the world from footage on the internet. In turn, the video model generates an observation trajectory plan, refining the LLM’s outline to incorporate new physical knowledge.This process, known as iterative refinement, allows HiP to reason about its ideas, taking in feedback at each stage to generate a more practical outline. The flow of feedback is similar to writing an article, where an author may send their draft to an editor, and with those revisions incorporated in, the publisher reviews for any last changes and finalizes.

      In this case, the top of the hierarchy is an egocentric action model, or a sequence of first-person images that infer which actions should take place based on its surroundings. During this stage, the observation plan from the video model is mapped over the space visible to the robot, helping the machine decide how to execute each task within the long-horizon goal. If a robot uses HiP to make tea, this means it will have mapped out exactly where the pot, sink, and other key visual elements are, and begin completing each sub-goal.Still, the multimodal work is limited by the lack of high-quality video foundation models. Once available, they could interface with HiP’s small-scale video models to further enhance visual sequence prediction and robot action generation. A higher-quality version would also reduce the current data requirements of the video models.That being said, the CSAIL team’s approach only used a tiny bit of data overall. Moreover, HiP was cheap to train and demonstrated the potential of using readily available foundation models to complete long-horizon tasks. “What Anurag has demonstrated is proof-of-concept of how we can take models trained on separate tasks and data modalities and combine them into models for robotic planning. In the future, HiP could be augmented with pre-trained models that can process touch and sound to make better plans,” says senior author Pulkit Agrawal, MIT assistant professor in EECS and director of the Improbable AI Lab. The group is also considering applying HiP to solving real-world long-horizon tasks in robotics.Ajay and Agrawal are lead authors on a paper describing the work. They are joined by MIT professors and CSAIL principal investigators Tommi Jaakkola, Joshua Tenenbaum, and Leslie Pack Kaelbling; CSAIL research affiliate and MIT-IBM AI Lab research manager Akash Srivastava; graduate students Seungwook Han and Yilun Du ’19; former postdoc Abhishek Gupta, who is now assistant professor at University of Washington; and former graduate student Shuang Li PhD ’23.

      The team’s work was supported, in part, by the National Science Foundation, the U.S. Defense Advanced Research Projects Agency, the U.S. Army Research Office, the U.S. Office of Naval Research Multidisciplinary University Research Initiatives, and the MIT-IBM Watson AI Lab. Their findings were presented at the 2023 Conference on Neural Information Processing Systems (NeurIPS). More

    • 113 Shares119 Views

      in Data Management & Statistics

      Image recognition accuracy: An unseen challenge confounding today’s AI

      by

      Imagine you are scrolling through the photos on your phone and you come across an image that at first you can’t recognize. It looks like maybe something fuzzy on the couch; could it be a pillow or a coat? After a couple of seconds it clicks — of course! That ball of fluff is your friend’s cat, Mocha. While some of your photos could be understood in an instant, why was this cat photo much more difficult?

      MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) researchers were surprised to find that despite the critical importance of understanding visual data in pivotal areas ranging from health care to transportation to household devices, the notion of an image’s recognition difficulty for humans has been almost entirely ignored. One of the major drivers of progress in deep learning-based AI has been datasets, yet we know little about how data drives progress in large-scale deep learning beyond that bigger is better.

      In real-world applications that require understanding visual data, humans outperform object recognition models despite the fact that models perform well on current datasets, including those explicitly designed to challenge machines with debiased images or distribution shifts. This problem persists, in part, because we have no guidance on the absolute difficulty of an image or dataset. Without controlling for the difficulty of images used for evaluation, it’s hard to objectively assess progress toward human-level performance, to cover the range of human abilities, and to increase the challenge posed by a dataset.

      To fill in this knowledge gap, David Mayo, an MIT PhD student in electrical engineering and computer science and a CSAIL affiliate, delved into the deep world of image datasets, exploring why certain images are more difficult for humans and machines to recognize than others. “Some images inherently take longer to recognize, and it’s essential to understand the brain’s activity during this process and its relation to machine learning models. Perhaps there are complex neural circuits or unique mechanisms missing in our current models, visible only when tested with challenging visual stimuli. This exploration is crucial for comprehending and enhancing machine vision models,” says Mayo, a lead author of a new paper on the work.

      This led to the development of a new metric, the “minimum viewing time” (MVT), which quantifies the difficulty of recognizing an image based on how long a person needs to view it before making a correct identification. Using a subset of ImageNet, a popular dataset in machine learning, and ObjectNet, a dataset designed to test object recognition robustness, the team showed images to participants for varying durations from as short as 17 milliseconds to as long as 10 seconds, and asked them to choose the correct object from a set of 50 options. After over 200,000 image presentation trials, the team found that existing test sets, including ObjectNet, appeared skewed toward easier, shorter MVT images, with the vast majority of benchmark performance derived from images that are easy for humans.

      The project identified interesting trends in model performance — particularly in relation to scaling. Larger models showed considerable improvement on simpler images but made less progress on more challenging images. The CLIP models, which incorporate both language and vision, stood out as they moved in the direction of more human-like recognition.

      “Traditionally, object recognition datasets have been skewed towards less-complex images, a practice that has led to an inflation in model performance metrics, not truly reflective of a model’s robustness or its ability to tackle complex visual tasks. Our research reveals that harder images pose a more acute challenge, causing a distribution shift that is often not accounted for in standard evaluations,” says Mayo. “We released image sets tagged by difficulty along with tools to automatically compute MVT, enabling MVT to be added to existing benchmarks and extended to various applications. These include measuring test set difficulty before deploying real-world systems, discovering neural correlates of image difficulty, and advancing object recognition techniques to close the gap between benchmark and real-world performance.”

      “One of my biggest takeaways is that we now have another dimension to evaluate models on. We want models that are able to recognize any image even if — perhaps especially if — it’s hard for a human to recognize. We’re the first to quantify what this would mean. Our results show that not only is this not the case with today’s state of the art, but also that our current evaluation methods don’t have the ability to tell us when it is the case because standard datasets are so skewed toward easy images,” says Jesse Cummings, an MIT graduate student in electrical engineering and computer science and co-first author with Mayo on the paper.

      From ObjectNet to MVT

      A few years ago, the team behind this project identified a significant challenge in the field of machine learning: Models were struggling with out-of-distribution images, or images that were not well-represented in the training data. Enter ObjectNet, a dataset comprised of images collected from real-life settings. The dataset helped illuminate the performance gap between machine learning models and human recognition abilities, by eliminating spurious correlations present in other benchmarks — for example, between an object and its background. ObjectNet illuminated the gap between the performance of machine vision models on datasets and in real-world applications, encouraging use for many researchers and developers — which subsequently improved model performance.

      Fast forward to the present, and the team has taken their research a step further with MVT. Unlike traditional methods that focus on absolute performance, this new approach assesses how models perform by contrasting their responses to the easiest and hardest images. The study further explored how image difficulty could be explained and tested for similarity to human visual processing. Using metrics like c-score, prediction depth, and adversarial robustness, the team found that harder images are processed differently by networks. “While there are observable trends, such as easier images being more prototypical, a comprehensive semantic explanation of image difficulty continues to elude the scientific community,” says Mayo.

      In the realm of health care, for example, the pertinence of understanding visual complexity becomes even more pronounced. The ability of AI models to interpret medical images, such as X-rays, is subject to the diversity and difficulty distribution of the images. The researchers advocate for a meticulous analysis of difficulty distribution tailored for professionals, ensuring AI systems are evaluated based on expert standards, rather than layperson interpretations.

      Mayo and Cummings are currently looking at neurological underpinnings of visual recognition as well, probing into whether the brain exhibits differential activity when processing easy versus challenging images. The study aims to unravel whether complex images recruit additional brain areas not typically associated with visual processing, hopefully helping demystify how our brains accurately and efficiently decode the visual world.

      Toward human-level performance

      Looking ahead, the researchers are not only focused on exploring ways to enhance AI’s predictive capabilities regarding image difficulty. The team is working on identifying correlations with viewing-time difficulty in order to generate harder or easier versions of images.

      Despite the study’s significant strides, the researchers acknowledge limitations, particularly in terms of the separation of object recognition from visual search tasks. The current methodology does concentrate on recognizing objects, leaving out the complexities introduced by cluttered images.

      “This comprehensive approach addresses the long-standing challenge of objectively assessing progress towards human-level performance in object recognition and opens new avenues for understanding and advancing the field,” says Mayo. “With the potential to adapt the Minimum Viewing Time difficulty metric for a variety of visual tasks, this work paves the way for more robust, human-like performance in object recognition, ensuring that models are truly put to the test and are ready for the complexities of real-world visual understanding.”

      “This is a fascinating study of how human perception can be used to identify weaknesses in the ways AI vision models are typically benchmarked, which overestimate AI performance by concentrating on easy images,” says Alan L. Yuille, Bloomberg Distinguished Professor of Cognitive Science and Computer Science at Johns Hopkins University, who was not involved in the paper. “This will help develop more realistic benchmarks leading not only to improvements to AI but also make fairer comparisons between AI and human perception.” 

      “It’s widely claimed that computer vision systems now outperform humans, and on some benchmark datasets, that’s true,” says Anthropic technical staff member Simon Kornblith PhD ’17, who was also not involved in this work. “However, a lot of the difficulty in those benchmarks comes from the obscurity of what’s in the images; the average person just doesn’t know enough to classify different breeds of dogs. This work instead focuses on images that people can only get right if given enough time. These images are generally much harder for computer vision systems, but the best systems are only a bit worse than humans.”

      Mayo, Cummings, and Xinyu Lin MEng ’22 wrote the paper alongside CSAIL Research Scientist Andrei Barbu, CSAIL Principal Research Scientist Boris Katz, and MIT-IBM Watson AI Lab Principal Researcher Dan Gutfreund. The researchers are affiliates of the MIT Center for Brains, Minds, and Machines.

      The team is presenting their work at the 2023 Conference on Neural Information Processing Systems (NeurIPS). More

    • 113 Shares119 Views

      in Data Management & Statistics

      Synthetic imagery sets new bar in AI training efficiency

      by

      Data is the new soil, and in this fertile new ground, MIT researchers are planting more than just pixels. By using synthetic images to train machine learning models, a team of scientists recently surpassed results obtained from traditional “real-image” training methods. 

      At the core of the approach is a system called StableRep, which doesn’t just use any synthetic images; it generates them through ultra-popular text-to-image models like Stable Diffusion. It’s like creating worlds with words. 

      So what’s in StableRep’s secret sauce? A strategy called “multi-positive contrastive learning.”

      “We’re teaching the model to learn more about high-level concepts through context and variance, not just feeding it data,” says Lijie Fan, MIT PhD student in electrical engineering, affiliate of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), lead researcher on the work. “When multiple images, all generated from the same text, all treated as depictions of the same underlying thing, the model dives deeper into the concepts behind the images, say the object, not just their pixels.”

      This approach considers multiple images spawned from identical text prompts as positive pairs, providing additional information during training, not just adding more diversity but specifying to the vision system which images are alike and which are different. Remarkably, StableRep outshone the prowess of top-tier models trained on real images, such as SimCLR and CLIP, in extensive datasets.

      “While StableRep helps mitigate the challenges of data acquisition in machine learning, it also ushers in a stride towards a new era of AI training techniques. The capacity to produce high-caliber, diverse synthetic images on command could help curtail cumbersome expenses and resources,” says Fan. 

      The process of data collection has never been straightforward. Back in the 1990s, researchers had to manually capture photographs to assemble datasets for objects and faces. The 2000s saw individuals scouring the internet for data. However, this raw, uncurated data often contained discrepancies when compared to real-world scenarios and reflected societal biases, presenting a distorted view of reality. The task of cleansing datasets through human intervention is not only expensive, but also exceedingly challenging. Imagine, though, if this arduous data collection could be distilled down to something as simple as issuing a command in natural language. 

      A pivotal aspect of StableRep’s triumph is the adjustment of the “guidance scale” in the generative model, which ensures a delicate balance between the synthetic images’ diversity and fidelity. When finely tuned, synthetic images used in training these self-supervised models were found to be as effective, if not more so, than real images.

      Taking it a step forward, language supervision was added to the mix, creating an enhanced variant: StableRep+. When trained with 20 million synthetic images, StableRep+ not only achieved superior accuracy but also displayed remarkable efficiency compared to CLIP models trained with a staggering 50 million real images.

      Yet, the path ahead isn’t without its potholes. The researchers candidly address several limitations, including the current slow pace of image generation, semantic mismatches between text prompts and the resultant images, potential amplification of biases, and complexities in image attribution, all of which are imperative to address for future advancements. Another issue is that StableRep requires first training the generative model on large-scale real data. The team acknowledges that starting with real data remains a necessity; however, when you have a good generative model, you can repurpose it for new tasks, like training recognition models and visual representations. 

      The team notes that they haven’t gotten around the need to start with real data; it’s just that once you have a good generative model you can repurpose it for new tasks, like training recognition models and visual representations. 

      While StableRep offers a good solution by diminishing the dependency on vast real-image collections, it brings to the fore concerns regarding hidden biases within the uncurated data used for these text-to-image models. The choice of text prompts, integral to the image synthesis process, is not entirely free from bias, “indicating the essential role of meticulous text selection or possible human curation,” says Fan. 

      “Using the latest text-to-image models, we’ve gained unprecedented control over image generation, allowing for a diverse range of visuals from a single text input. This surpasses real-world image collection in efficiency and versatility. It proves especially useful in specialized tasks, like balancing image variety in long-tail recognition, presenting a practical supplement to using real images for training,” says Fan. “Our work signifies a step forward in visual learning, towards the goal of offering cost-effective training alternatives while highlighting the need for ongoing improvements in data quality and synthesis.”

      “One dream of generative model learning has long been to be able to generate data useful for discriminative model training,” says Google DeepMind researcher and University of Toronto professor of computer science David Fleet, who was not involved in the paper. “While we have seen some signs of life, the dream has been elusive, especially on large-scale complex domains like high-resolution images. This paper provides compelling evidence, for the first time to my knowledge, that the dream is becoming a reality. They show that contrastive learning from massive amounts of synthetic image data can produce representations that outperform those learned from real data at scale, with the potential to improve myriad downstream vision tasks.”

      Fan is joined by Yonglong Tian PhD ’22 as lead authors of the paper, as well as MIT associate professor of electrical engineering and computer science and CSAIL principal investigator Phillip Isola; Google researcher and OpenAI technical staff member Huiwen Chang; and Google staff research scientist Dilip Krishnan. The team will present StableRep at the 2023 Conference on Neural Information Processing Systems (NeurIPS) in New Orleans. More

    • 163 Shares129 Views

      in Data Management & Statistics

      To excel at engineering design, generative AI must learn to innovate, study finds

      by

      ChatGPT and other deep generative models are proving to be uncanny mimics. These AI supermodels can churn out poems, finish symphonies, and create new videos and images by automatically learning from millions of examples of previous works. These enormously powerful and versatile tools excel at generating new content that resembles everything they’ve seen before.

      But as MIT engineers say in a new study, similarity isn’t enough if you want to truly innovate in engineering tasks.

      “Deep generative models (DGMs) are very promising, but also inherently flawed,” says study author Lyle Regenwetter, a mechanical engineering graduate student at MIT. “The objective of these models is to mimic a dataset. But as engineers and designers, we often don’t want to create a design that’s already out there.”

      He and his colleagues make the case that if mechanical engineers want help from AI to generate novel ideas and designs, they will have to first refocus those models beyond “statistical similarity.”

      “The performance of a lot of these models is explicitly tied to how statistically similar a generated sample is to what the model has already seen,” says co-author Faez Ahmed, assistant professor of mechanical engineering at MIT. “But in design, being different could be important if you want to innovate.”

      In their study, Ahmed and Regenwetter reveal the pitfalls of deep generative models when they are tasked with solving engineering design problems. In a case study of bicycle frame design, the team shows that these models end up generating new frames that mimic previous designs but falter on engineering performance and requirements.

      When the researchers presented the same bicycle frame problem to DGMs that they specifically designed with engineering-focused objectives, rather than only statistical similarity, these models produced more innovative, higher-performing frames.

      The team’s results show that similarity-focused AI models don’t quite translate when applied to engineering problems. But, as the researchers also highlight in their study, with some careful planning of task-appropriate metrics, AI models could be an effective design “co-pilot.”

      “This is about how AI can help engineers be better and faster at creating innovative products,” Ahmed says. “To do that, we have to first understand the requirements. This is one step in that direction.”

      The team’s new study appeared recently online, and will be in the December print edition of the journal Computer Aided Design. The research is a collaboration between computer scientists at MIT-IBM Watson AI Lab and mechanical engineers in MIT’s DeCoDe Lab. The study’s co-authors include Akash Srivastava and Dan Gutreund at the MIT-IBM Watson AI Lab.

      Framing a problem

      As Ahmed and Regenwetter write, DGMs are “powerful learners, boasting unparalleled ability” to process huge amounts of data. DGM is a broad term for any machine-learning model that is trained to learn distribution of data and then use that to generate new, statistically similar content. The enormously popular ChatGPT is one type of deep generative model known as a large language model, or LLM, which incorporates natural language processing capabilities into the model to enable the app to generate realistic imagery and speech in response to conversational queries. Other popular models for image generation include DALL-E and Stable Diffusion.

      Because of their ability to learn from data and generate realistic samples, DGMs have been increasingly applied in multiple engineering domains. Designers have used deep generative models to draft new aircraft frames, metamaterial designs, and optimal geometries for bridges and cars. But for the most part, the models have mimicked existing designs, without improving the performance on existing designs.

      “Designers who are working with DGMs are sort of missing this cherry on top, which is adjusting the model’s training objective to focus on the design requirements,” Regenwetter says. “So, people end up generating designs that are very similar to the dataset.”

      In the new study, he outlines the main pitfalls in applying DGMs to engineering tasks, and shows that the fundamental objective of standard DGMs does not take into account specific design requirements. To illustrate this, the team invokes a simple case of bicycle frame design and demonstrates that problems can crop up as early as the initial learning phase. As a model learns from thousands of existing bike frames of various sizes and shapes, it might consider two frames of similar dimensions to have similar performance, when in fact a small disconnect in one frame — too small to register as a significant difference in statistical similarity metrics — makes the frame much weaker than the other, visually similar frame.

      Beyond “vanilla”
      An animation depicting transformations across common bicycle designs. Credit: Courtesy of the researchers

      The researchers carried the bicycle example forward to see what designs a DGM would actually generate after having learned from existing designs. They first tested a conventional “vanilla” generative adversarial network, or GAN — a model that has widely been used in image and text synthesis, and is tuned simply to generate statistically similar content. They trained the model on a dataset of thousands of bicycle frames, including commercially manufactured designs and less conventional, one-off frames designed by hobbyists.

      Once the model learned from the data, the researchers asked it to generate hundreds of new bike frames. The model produced realistic designs that resembled existing frames. But none of the designs showed significant improvement in performance, and some were even a bit inferior, with heavier, less structurally sound frames.

      The team then carried out the same test with two other DGMs that were specifically designed for engineering tasks. The first model is one that Ahmed previously developed to generate high-performing airfoil designs. He built this model to prioritize statistical similarity as well as functional performance. When applied to the bike frame task, this model generated realistic designs that also were lighter and stronger than existing designs. But it also produced physically “invalid” frames, with components that didn’t quite fit or overlapped in physically impossible ways.

      “We saw designs that were significantly better than the dataset, but also designs that were geometrically incompatible because the model wasn’t focused on meeting design constraints,” Regenwetter says.

      The last model the team tested was one that Regenwetter built to generate new geometric structures. This model was designed with the same priorities as the previous models, with the added ingredient of design constraints, and prioritizing physically viable frames, for instance, with no disconnections or overlapping bars. This last model produced the highest-performing designs, that were also physically feasible.

      “We found that when a model goes beyond statistical similarity, it can come up with designs that are better than the ones that are already out there,” Ahmed says. “It’s a proof of what AI can do, if it is explicitly trained on a design task.”

      For instance, if DGMs can be built with other priorities, such as performance, design constraints, and novelty, Ahmed foresees “numerous engineering fields, such as molecular design and civil infrastructure, would greatly benefit. By shedding light on the potential pitfalls of relying solely on statistical similarity, we hope to inspire new pathways and strategies in generative AI applications outside multimedia.” More