Constellation: Learning relational abstractions over objects for compositional imagination
Learning structured representations of visual scenes is currently a major bottleneck to bridging perception with reasoning. While there has been exciting progress with slot-based models, which learn to segment scenes into sets of objects, learning configurational properties of entire groups of objects is still under-explored. To address this problem, we introduce Constellation, a network that learns relational abstractions of static visual scenes, and generalises these abstractions over sensory particularities, thus offering a potential basis for abstract relational reasoning. We further show that this basis, along with language association, provides a means to imagine sensory content in new ways. This work is a first step in the explicit representation of visual relationships and using them for complex cognitive procedures.
Code (0)
등록된 구현이 없습니다.
Tasks
Relational ReasoningSimilar Papers 제목 키워드 기반
Compositional diversity in visual concept learning
Humans leverage compositionality to efficiently learn new concepts, understanding how familiar parts can combine together to form novel objects. In contrast, popular computer vision models struggle to make the same types…
DiversityProgram inductionRelational Abstractions for Generalized Reinforcement Learning on Symbolic Problems
Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes relational abstractions in conjunction with …
Objectreinforcement-learningReinforcement LearningReinforcement Learning (RL)A Study of Compositional Generalization in Neural Models
Compositional and relational learning is a hallmark of human intelligence, but one which presents challenges for neural models. One difficulty in the development of such models is the lack of benchmarks with clear compos…
image-classificationImage ClassificationRelational ReasoningCompositional Abstractions of Interconnected Discrete-Time Switched Systems
In this paper, we introduce a compositional method for the construction of finite abstractions of interconnected discrete-time switched systems. Particularly, we use a notion of so-called alternating simulation function …
RelationAnswer-Set-Programming-based Abstractions for Reinforcement Learning
Reinforcement Learning (RL) enables autonomous agents to learn policies from experience, but realistic problems often involve enormous state spaces, making learning and generalisation challenging. Abstraction and approxi…
Reinforcement Learning