Object-Centric Learning with Slot Attention

TL;DR

This paper introduces Slot Attention, a novel neural module that produces exchangeable, object-centric representations from perceptual inputs, enabling better generalization in scene understanding tasks.

Contribution

The paper presents Slot Attention, a new architectural component that extracts object-centric representations, improving compositional understanding in neural networks.

Findings

Slot Attention effectively extracts object-centric representations.

The method generalizes well to unseen object compositions.

It performs successfully on unsupervised discovery and supervised property prediction tasks.

Abstract

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions when trained on unsupervised object discovery and supervised property prediction tasks.