Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models
The ability to discover abstract physical concepts and understand how they work in the world through observing lies at the core of human intelligence. The acquisition of this ability is based on compositionally perceiving the environment in terms of objects and relations in an unsupervised manner. Recent approaches learn object-centric representations and capture visually observable concepts of objects, e.g., shape, size, and location. In this paper, we take a step forward and try to discover and represent intrinsic physical concepts such as mass and charge. We introduce the PHYsical Concepts Inference NEtwork (PHYCINE), a system that infers physical concepts in different abstract levels without supervision. The key insights underlining PHYCINE are two-fold, commonsense knowledge emerges with prediction, and physical concepts of different abstract levels should be reasoned in a bottom-up fashion. Empirical evaluation demonstrates that variables inferred by our system work in accordance with the properties of the corresponding physical concepts. We also show that object representations containing the discovered physical concepts variables could help achieve better performance in causal reasoning tasks, i.e., ComPhy.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Language-Mediated, Object-Centric Representation Learning
We present Language-mediated, Object-centric Representation Learning (LORL), a paradigm for learning disentangled, object-centric scene representations from vision and language. LORL builds upon recent advances in unsupe…
ObjectObject DiscoveryReferring ExpressionReferring Expression Comprehension+3Unsupervised Discovery of Object-Centric Neural Fields
We study inferring 3D object-centric scene representations from a single image. While recent methods have shown potential in unsupervised 3D object discovery from simple synthetic images, they fail to generalize to real-…
ObjectObject DiscoverySemantic SegmentationSystematic Generalization+1Unsupervised Musical Object Discovery from Audio
Current object-centric learning models such as the popular SlotAttention architecture allow for unsupervised visual scene decomposition. Our novel MusicSlots method adapts SlotAttention to the audio domain, to achieve un…
ObjectObject DiscoveryProperty PredictionDiscovering physical concepts with neural networks
Despite the success of neural networks at solving concrete physics problems, their use as a general-purpose tool for scientific discovery is still in its infancy. Here, we approach this problem by modelling a neural netw…
Representation Learningscientific discoveryTime Series AnalysisEnhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery
Concept-based explainable approaches have emerged as a promising method in explainable AI because they can interpret models in a way that aligns with human reasoning. However, their adaption in the text domain remains li…