Unsupervised Object Localization: Observing the Background to Discover Objects

TL;DR

This paper introduces FOUND, a simple unsupervised model that discovers salient objects by focusing on background cues, achieving state-of-the-art results in unsupervised saliency detection, object discovery, and semantic segmentation retrieval.

Contribution

The paper proposes a novel background-focused approach for unsupervised object discovery, using a single convolutional layer initialized with background masks from self-supervised representations.

Findings

State-of-the-art results on unsupervised saliency detection benchmarks

Effective object discovery without explicit object supervision

Good performance in unsupervised semantic segmentation retrieval

Abstract

Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is a very hard task; what are the desired objects, when to separate them into parts, how many are there, and of what classes? The answers to these questions depend on the tasks and datasets of evaluation. In this work, we take a different approach and propose to look for the background instead. This way, the salient objects emerge as a by-product without any strong assumption on what an object should be. We propose FOUND, a simple model made of a single $conv1\times1$ initialized with coarse background masks extracted from self-supervised patch-based representations. After fast training and refining these seed masks, the model reaches state-of-the-art results on unsupervised saliency detection and object discovery benchmarks. Moreover, we show that our approach yields good results in the unsupervised semantic segmentation retrieval task. The code to reproduce our results is available at https://github.com/valeoai/FOUND.