Early in development, infants learn a range of useful concepts, which can be challenging from a computational standpoint. This early learning comes together with an initial understanding of aspects of the meaning of concepts, e.g., their implications, causality, and using them to predict likely future events. All this is accomplished in many cases with little or no supervision, and from relatively few examples, compared with current network models. In learning about objects and human-object interactions, early acquired and possibly innate concepts are often used in the process of learning additional, more complex concepts. In the current work, we model how early-acquired concepts are used in the learning of subsequent concepts, and compare the results with standard deep network modeling. We focused in particular on the use of the concepts of animacy and goal attribution in learning to predict future events. We show that the use of early concepts in the learning of new concepts leads to better learning (higher accuracy) and more efficient learning (requiring less data). We further show that this integration of early and new concepts shapes the representation of the concepts acquired by the model. The results show that when the concepts were learned in a human-like manner, the emerging representation was more useful, as measured in terms of generalization to novel data and tasks. On a more general level, the results suggest that there are likely to be basic differences in the conceptual structures acquired by current network models compared to human learning.

Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to be adjusted to suit the objectives of new tasks, resulting in a phenomenon called catastrophic forgetting. Most approaches to this problem seek a balance between maximizing performance on the new tasks and minimizing the forgetting of previous tasks. In contrast, our approach attempts to maximize the performance of the new task, while ensuring zero forgetting. This is accomplished by creating a task-specific modulation parameters for each task. Only these would be learnable parameters during learning of consecutive tasks. Through comprehensive experimental evaluations, our model demonstrates superior performance in acquiring and retaining novel tasks that pose difficulties for other multi-task models. This emphasizes the efficacy of our approach in preventing catastrophic forgetting while accommodating the acquisition of new tasks

Cortical processing, in vision and other domains, combines bottom-up (BU) with extensive top-down (TD) processing. Two primary goals attributed to TD processing are learning and directing attention. These two roles are accomplished in current network models through distinct mechanisms. Attention guidance is often implemented by extending the model's architecture, while learning is typically accomplished by an external learning algorithm such as back-propagation. In the current work, we present an integration of the two functions above, which appear unrelated, using a single unified mechanism inspired by the human brain. We propose a novel symmetric bottom-up top-down network structure that can integrate conventional bottom-up networks with a symmetric top-down counterpart, allowing each network to recurrently guide and influence the other. For example, during multi-task learning, the same top-down network is being used for both learning, via propagating feedback signals, and at the same time also for top-down attention, by guiding the bottom-up network to perform a selected task. In contrast with standard models, no external back-propagation is used for learning. Instead, we propose a 'Counter-Hebb' learning, which adjusts the weights of both the bottom-up and top-down networks simultaneously. We show that our method achieves competitive performance on standard multi-task learning benchmarks. Yet, unlike existing methods, we rely on single-task architectures and optimizers, without any task-specific parameters. The results, which show how attention-guided multi-tasks can be combined efficiently with internal learning in a unified TD process, suggest a possible model for combining BU and TD processing in human vision.

We describe a computational model of humans' ability to provide a detailed interpretation of components in a scene. Humans can identify in an image meaningful components almost everywhere, and identifying these components is an essential part of the visual process, and of understanding the surrounding scene and its potential meaning to the viewer. Detailed interpretation is beyond the scope of current models of visual recognition. Our model suggests that this is a fundamental limitation, related to the fact that existing models rely on feed-forward but limited top-down processing. In our model, a first recognition stage leads to the initial activation of class candidates, which is incomplete and with limited accuracy. This stage then triggers the application of class-specific interpretation and validation processes, which recover richer and more accurate interpretation of the visible scene. We discuss implications of the model for visual interpretation by humans and by computer vision models.

Published as a workshop paper at "Bridging AI and Cognitive Science" (ICLR 2020) In human vision objects and their parts can be visually recognized from purely spatial or purely temporal information but the mechanisms integrating space and time are poorly understood. Here we show that human visual recognition of objects and actions can be achieved by efficiently combining spatial and motion cues in configurations where each source on its own is insufficient for recognition. This analysis is obtained by identifying minimal videos: these are short and tiny video clips in which objects, parts, and actions can be reliably recognized, but any reduction in either space or time makes them unrecognizable. State-of-the-art deep networks for dynamic visual recognition cannot replicate human behavior in these configurations. This gap between humans and machines points to critical mechanisms in human dynamic vision that are lacking in current models.

Rich empirical evidence has shown that visual object recognition in the brain is fast and effortless, with relevant brain signals reported to start as early as 80 ms. Here we study the time trajectory of the recognition process at the level of minimal recognizable images (termed MIRC). These are images that can be recognized reliably, but in which a minute change of the image (reduction by either size or resolution) has a drastic effect on recognition. Subjects were assigned to one of nine exposure conditions: 200, 500, 1000, 2000 ms with or without masking, as well as unlimited time. The subjects were not limited in time to respond after presentation. The results show that in the masked conditions, recognition rates develop gradually over an extended period, e.g. average of 18% for 200 ms exposure and 45% for 500 ms, increasing significantly with longer exposure even above 2 secs. When presented for unlimited time (until response), MIRC recognition rates were equivalent to the rates of full-object images presented for 50 ms followed by masking. What takes the brain so long to recognize such images? We discuss why processes involving eye-movements, perceptual decision-making and pattern completion are unlikely explanations. Alternatively, we hypothesize that MIRC recognition requires an extended top-down process complementing the feed-forward phase.

This paper presents an approach to the visual recognition of human actions using only single images as input. The task is easy for humans but difficult for current approaches to object recognition, because action instances may be similar in terms of body pose, and often require detailed examination of relations between participating objects and body parts in order to be recognized. The proposed approach applies a two-stage interpretation procedure to each training and test image. The first stage produces accurate detection of the relevant body parts of the actor, forming a prior for the local evidence needed to be considered for identifying the action. The second stage extracts features that are'anchored' to the detected body parts, and uses these features and their feature-to-part relations in order to recognize the action.

Joint visual attention is characterized by two or more individuals looking at a common target at the same time. The ability to identify joint attention in scenes, the people involved, and their common target, is fundamental to the understanding of social interactions, including others' intentions and goals. In this work we deal with the extraction of joint attention events, and the use of such events for image descriptions. The work makes two novel contributions. First, our extraction algorithm is the first which identifies joint visual attention in single static images. It computes 3D gaze direction, identifies the gaze target by combining gaze direction with a 3D depth map computed for the image, and identifies the common gaze target. Second, we use a human study to demonstrate the sensitivity of humans to joint attention, suggesting that the detection of such a configuration in an image can be useful for understanding the image, including the goals of the agents and their joint activity, and therefore can contribute to image captioning and related tasks.

Combinatorial optimization is a common theme in computer science which underlies a considerable variety of problems. In contrast to the continuous setting, combinatorial problems require special solution strategies, and it's hard to come by generic schemes like gradient methods for continuous domains. We follow a standard construction of a parametric sampling distribution that transforms the problem to the continuous domain, allowing us to optimize the expectation of a given objective using estimates of the gradient. In spite of the apparent generality, such constructions are known to suffer from highly variable gradient estimates, and thus require careful tuning that is done in a problem specific manner. We show that a simple trick of converting the objective values to their cumulative probabilities fixes the distribution of the objective, allowing us to derive an online optimization algorithm that can be applied in a generic fashion. As an experimental benchmark we use the task of finding cliques in undirected graphs, and we show that our method, even when blindly applied, consistently outperforms related methods. Notably, on the DIMACS clique benchmark, our method approaches the performance of the best clique finding algorithms without access to the graph structure, and only through objective function evaluations, thus providing significant evidence to the generality and effectivity of our method.

For many tasks and data types, there are natural transformations to which the data should be invariant or insensitive. For instance, in visual recognition, natural images should be insensitive to rotation and translation. This requirement and its implications have been important in many machine learning applications, and tolerance for image transformations was primarily achieved by using robust feature vectors. In this paper we propose a novel and computationally efficient way to learn a local Mahalanobis metric per datum, and show how we can learn a local invariant metric to any transformation in order to improve performance.