Learning Global Object-Centric Representations via Disentangled Slot Attention

TL;DR

This paper presents a novel object-centric learning approach that enables AI to identify objects across different scenes and generate diverse scenes with specific objects by learning global, invariant object representations.

Contribution

It introduces a Disentangled Slot Attention module that separates scene-dependent attributes from scene-independent object features, enhancing object identification and scene generation capabilities.

Findings

Effective global object-centric representations learned

Improved object identification across scenes

Enhanced scene generation with specific objects

Abstract

Humans can discern scene-independent features of objects across various environments, allowing them to swiftly identify objects amidst changing factors such as lighting, perspective, size, and position and imagine the complete images of the same object in diverse settings. Existing object-centric learning methods only extract scene-dependent object-centric representations, lacking the ability to identify the same object across scenes as humans. Moreover, some existing methods discard the individual object generation capabilities to handle complex scenes. This paper introduces a novel object-centric learning method to empower AI systems with human-like capabilities to identify objects across scenes and generate diverse scenes containing specific objects by learning a set of global object-centric representations. To learn the global object-centric representations that encapsulate globally invariant attributes of objects (i.e., the complete appearance and shape), this paper designs a Disentangled Slot Attention module to convert the scene features into scene-dependent attributes (such as scale, position and orientation) and scene-independent representations (i.e., appearance and shape). Experimental results substantiate the efficacy of the proposed method, demonstrating remarkable proficiency in global object-centric representation learning, object identification, scene generation with specific objects and scene decomposition.