Object-Oriented Learning (OOL): Perception, Representation, and Reasoning

International Conference on Machine Learning (ICML)

Friday July 17, 2020, Virtual Workshop

Access the virtual workshop page

Hierarchical Relational Inference

Aleksandar Stanic, Sjoerd van Steenkiste, and Jürgen Schmidhuber
PDF · Join Meeting Room · See ICML Portal for password

Common-sense physical reasoning requires learning about the interactions of objects and their dynamics. The notion of an abstract object, however, encompasses a wide variety of physical objects that differ greatly in terms of the complex behaviors they support. To address this, we propose a novel approach to physical reasoning that models objects as hierarchies of parts that may locally behave separately, but also act more globally as a single whole. Unlike prior approaches, our method learns in an unsupervised fashion directly from raw visual images to discover objects, parts, and their relations. We demonstrate how it improves over a strong baseline at modeling synthetic and real-world physical dynamics.