Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention

TL;DR

This paper introduces a probabilistic slot-attention method that guarantees the identifiability of object-centric representations without supervision, supported by theoretical analysis and empirical validation on various datasets.

Contribution

It presents a novel probabilistic approach to slot attention that offers theoretical guarantees for object representation identifiability in an unsupervised setting.

Findings

Theoretical identifiability guarantees are established for the proposed method.

Empirical validation confirms the approach works on both simple and complex datasets.

The method enables scalable, correct object-centric representations without supervision.

Abstract

Learning modular object-centric representations is crucial for systematic generalization. Existing methods show promising object-binding capabilities empirically, but theoretical identifiability guarantees remain relatively underdeveloped. Understanding when object-centric representations can theoretically be identified is crucial for scaling slot-based methods to high-dimensional images with correctness guarantees. To that end, we propose a probabilistic slot-attention algorithm that imposes an aggregate mixture prior over object-centric slot representations, thereby providing slot identifiability guarantees without supervision, up to an equivalence relation. We provide empirical verification of our theoretical identifiability result using both simple 2-dimensional data and high-resolution imaging datasets.