Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context

TL;DR

This paper introduces a self-supervised, end-to-end framework for unsupervised salient object detection that leverages top-down context and contrastive learning to improve semantic understanding and suppress non-salient objects.

Contribution

It proposes a novel self-supervised approach with a detail-boosting refiner and non-salient suppression, advancing unsupervised saliency detection without relying on noisy labels.

Findings

Achieves state-of-the-art performance among end-to-end unsupervised methods.

Effectively suppresses non-salient objects in diverse scenarios.

Demonstrates robustness and accuracy on benchmark datasets.

Abstract

Unsupervised salient object detection aims to detect salient objects without using supervision signals eliminating the tedious task of manually labeling salient objects. To improve training efficiency, end-to-end methods for USOD have been proposed as a promising alternative. However, current solutions rely heavily on noisy handcraft labels and fail to mine rich semantic information from deep features. In this paper, we propose a self-supervised end-to-end salient object detection framework via top-down context. Specifically, motivated by contrastive learning, we exploit the self-localization from the deepest feature to construct the location maps which are then leveraged to learn the most instructive segmentation guidance. Further considering the lack of detailed information in deepest features, we exploit the detail-boosting refiner module to enrich the location labels with details. Moreover, we observe that due to lack of supervision, current unsupervised saliency models tend to detect non-salient objects that are salient in some other samples of corresponding scenarios. To address this widespread issue, we design a novel Unsupervised Non-Salient Suppression (UNSS) method developing the ability to ignore non-salient objects. Extensive experiments on benchmark datasets demonstrate that our method achieves leading performance among the recent end-to-end methods and most of the multi-stage solutions. The code is available.