Sparse Relational Reasoning with Object-Centric Representations
We investigate the composability of soft-rules learned by relational neural architectures when operating over object-centric (slot-based) representations, under a variety of sparsity-inducing constraints. We find that increasing sparsity, especially on features, improves the performance of some models and leads to simpler relations. Additionally, we observe that object-centric representations can be detrimental when not all objects are fully captured; a failure mode to which CNNs are less prone. These findings demonstrate the trade-offs between interpretability and performance, even for models designed to tackle relational tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectRelational ReasoningSimilar Papers 제목 키워드 기반
Edge-Centric Relational Reasoning for 3D Scene Graph Prediction
3D scene graph prediction aims to abstract complex 3D environments into structured graphs consisting of objects and their pairwise relationships. Existing approaches typically adopt object-centric graph neural networks, …
Relational ReasoningGraph Neural NetworkSystematic Visual Reasoning through Object-Centric Relational Abstraction
Human visual reasoning is characterized by an ability to identify abstract patterns from only a small number of examples, and to systematically generalize those patterns to novel inputs. This capacity depends in large pa…
ObjectSystematic GeneralizationVisual ReasoningAgent-Centric Representations for Multi-Agent Reinforcement Learning
Object-centric representations have recently enabled significant progress in tackling relational reasoning tasks. By building a strong object-centric inductive bias into neural architectures, recent efforts have improved…
Inductive BiasMulti-agent Reinforcement LearningObjectreinforcement-learning+4OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad
Although foundation models (FMs) claim to be powerful, their generalization ability significantly decreases when faced with distribution shifts, weak supervision, or malicious attacks in the open world. On the other hand…
Domain GeneralizationRelationRelational ReasoningRelational inductive bias for physical construction in humans and machines
While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks. We hypothesize that what these …
Deep Reinforcement LearningInductive BiasObjectReinforcement Learning