Related papers: Object-centric proto-symbolic behavioural reasonin…
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…
Humans perceive and interact with hundreds of objects every day. In doing so, they need to employ mental models of these objects and often exploit symmetries in the object's shape and appearance in order to learn generalizable and…
Object-centric world models (OCWM) aim to decompose visual scenes into object-level representations, providing structured abstractions that could improve compositional generalization and data efficiency in reinforcement learning. We…
Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information…
An effective way to achieve intelligence is to simulate various intelligent behaviors in the human brain. In recent years, bio-inspired learning methods have emerged, and they are different from the classical mathematical programming…
Building perceptual systems for robotics which perform well under tight computational budgets requires novel architectures which rethink the traditional computer vision pipeline. Modern vision architectures require the agent to build a…
Vision guided navigation requires processing complex visual information to inform task-orientated decisions. Applications include autonomous robots, self-driving cars, and assistive vision for humans. A key element is the extraction and…
As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…
Animal vision is thought to optimize various objectives from metabolic efficiency to discrimination performance, yet its ultimate objective is to facilitate the survival of the animal within its ecological niche. However, modeling animal…
Interventions are central to causal learning and reasoning. Yet ultimately an intervention is an abstraction: an agent embedded in a physical environment (perhaps modeled as a Markov decision process) does not typically come equipped with…
This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. This is done using a combination of object-wise…
Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel…
We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some…
The unification of low-level perception and high-level reasoning is a long-standing problem in artificial intelligence, which has the potential to not only bring the areas of logic and learning closer together but also demonstrate how…
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…
Much of the remarkable progress in computer vision has been focused around fully supervised learning mechanisms relying on highly curated datasets for a variety of tasks. In contrast, humans often learn about their world with little to no…
Recent advances in deep learning have led to a data-centric intelligence i.e. artificially intelligent models unlocking the potential to ingest a large amount of data and be really good at performing digital tasks such as text-to-image…
In this paper, we propose a concept learning architecture that enables a robot to build symbols through self-exploration by interacting with a varying number of objects. Our aim is to allow a robot to learn concepts without constraints,…
In this paper, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continuous interaction of a manipulator robot with multiple objects…
The success of smart environments largely depends on their smartness of understanding the environments' ongoing situations. Accordingly, this task is an essence to smart environment central processors. Obtaining knowledge from the…