Large-Scale Unsupervised Object Discovery

TL;DR

This paper introduces a scalable, fully unsupervised object discovery method that formulates the task as a ranking problem, leveraging self-supervised features and distributed eigenvalue techniques, achieving state-of-the-art results on large datasets.

Contribution

The paper presents a novel scalable formulation of unsupervised object discovery as a ranking problem using self-supervised features, enabling effective large-scale application.

Findings

Outperforms existing methods on COCO and OpenImages datasets.

Achieves over 37% improvement in single-object discovery at large scale.

Surpasses other algorithms in multi-object discovery with over 14% higher average precision.

Abstract

Existing approaches to unsupervised object discovery (UOD) do not scale up to large datasets without approximations that compromise their performance. We propose a novel formulation of UOD as a ranking problem, amenable to the arsenal of distributed methods available for eigenvalue problems and link analysis. Through the use of self-supervised features, we also demonstrate the first effective fully unsupervised pipeline for UOD. Extensive experiments on COCO and OpenImages show that, in the single-object discovery setting where a single prominent object is sought in each image, the proposed LOD (Large-scale Object Discovery) approach is on par with, or better than the state of the art for medium-scale datasets (up to 120K images), and over 37% better than the only other algorithms capable of scaling up to 1.7M images. In the multi-object discovery setting where multiple objects are sought in each image, the proposed LOD is over 14% better in average precision (AP) than all other methods for datasets ranging from 20K to 1.7M images. Using self-supervised features, we also show that the proposed method obtains state-of-the-art UOD performance on OpenImages. Our code is publicly available at https://github.com/huyvvo/LOD.