Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context
Open Access
- 26 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 5532-5541
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.Keywords
All Related Versions
Funding Information
- Scientific and Technological Innovation Action Plan of Shanghai Science and Technology Committee (22511102202)
- National Natural Science Foundation of China (62072112)
- National Key R&D Program of China (2020AAA0108301)
This publication has 44 references indexed in Scilit:
- Learning Deep Features for Discriminative Localization2016
- Efficient Saliency-Based Object Detection in Remote Sensing Images Using Deep Belief NetworksIEEE Geoscience and Remote Sensing Letters, 2016
- FaceNet: A unified embedding for face recognition and clustering2015
- Deep networks for saliency detection via local estimation and global search2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Saliency Detection via Dense and Sparse Reconstruction2013
- Hierarchical Saliency Detection2013
- Saliency Detection via Graph-Based Manifold Ranking2013
- Learning to Detect a Salient ObjectIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005