Related papers: Learning a metacognition for object perception

In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step…

Humans are able to segment images effortlessly without supervision using perceptual grouping. Here, we propose a counter-intuitive computational approach to solving unsupervised perceptual grouping and segmentation: that they arise because…

In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use…

Machine learning algorithms have achieved superhuman performance in specific complex domains. However, learning online from few examples and compositional learning for efficient generalization across domains remain elusive. In humans, such…

Object-based attention is a key component of the visual system, relevant for perception, learning, and memory. Neurons tuned to features of attended objects tend to be more active than those associated with non-attended objects. There is a…

Simulation plays a key role in scaling robot learning and validating policies, but constructing simulations remains a labor-intensive process. This paper introduces ReGen, a generative simulation framework that automates simulation design…

Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator.…

Language acquisition is the process of learning words from the surrounding scene. We introduce a meta-learning framework that learns how to learn word representations from unconstrained scenes. We leverage the natural compositional…

When interacting with the world robots face a number of difficult questions, having to make decisions when given under-specified tasks where they need to make choices, often without clearly defined right and wrong answers. Humans, on the…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

How the human vision system addresses the object identity-preserving recognition problem is largely unknown. Here, we use a vision recognition-reconstruction network (RRN) to investigate the development, recognition, learning and forgetting…

Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new…

Machine Learning and Inference methods have become ubiquitous in our attempt to induce more abstract representations of natural language text, visual scenes, and other messy, naturally occurring data, and support decisions that depend on…

The sound of crashing waves, the roar of fast-moving cars -- sound conveys important information about the objects in our surroundings. In this work, we show that ambient sounds can be used as a supervisory signal for learning visual…

Meta-learning aims to develop algorithms that can learn from other learning algorithms to adapt to new and changing environments. This requires a model of how other learning algorithms operate and perform in different contexts, which is…

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…

Local and global patterns of an object are closely related. Although each part of an object is incomplete, the underlying attributes about the object are shared among all parts, which makes reasoning the whole object from a single part…

Confidence-aware learning is proven as an effective solution to prevent networks becoming overconfident. We present a confidence-aware camouflaged object detection framework using dynamic supervision to produce both accurate camouflage map…

Creating high-quality and realistic images is now possible thanks to the impressive advancements in image generation. A description in natural language of your desired output is all you need to obtain breathtaking results. However, as the…

In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful…