Bootstrapping Top-down Information for Self-modulating Slot Attention

TL;DR

This paper introduces a novel object-centric learning framework that incorporates a top-down pathway to bootstrap object semantics and dynamically modulate features, improving representation quality in complex visual scenes.

Contribution

It presents a new OCL method with a top-down pathway that enhances object representations by self-modulating based on bootstrap semantics, outperforming existing approaches.

Findings

Achieves state-of-the-art results on synthetic benchmarks.

Improves object representation in complex visual environments.

Demonstrates effectiveness of top-down modulation in OCL.

Abstract

Object-centric learning (OCL) aims to learn representations of individual objects within visual scenes without manual supervision, facilitating efficient and effective visual reasoning. Traditional OCL methods primarily employ bottom-up approaches that aggregate homogeneous visual features to represent objects. However, in complex visual environments, these methods often fall short due to the heterogeneous nature of visual features within an object. To address this, we propose a novel OCL framework incorporating a top-down pathway. This pathway first bootstraps the semantics of individual objects and then modulates the model to prioritize features relevant to these semantics. By dynamically modulating the model based on its own output, our top-down pathway enhances the representational quality of objects. Our framework achieves state-of-the-art performance across multiple synthetic and real-world object-discovery benchmarks.