Projects per year
Abstract
Fully-supervised salient object detection (SOD) methods have made great progress, but such methods often rely on a large number of pixel-level annotations, which are time-consuming and labour-intensive. In this paper, we focus on a new weakly-supervised SOD task under hybrid labels, where the supervision labels include a large number of coarse labels generated by the traditional unsupervised method and a small number of real labels. To address the issues of label noise and quantity imbalance in this task, we design a new pipeline framework with three sophisticated training strategies. In terms of model framework, we decouple the task into label refinement sub-task and salient object detection sub-task, which cooperate with each other and train alternately. Specifically, the R-Net is designed as a two-stream encoder-decoder model equipped with Blender with Guidance and Aggregation Mechanisms (BGA), aiming to rectify the coarse labels for more reliable pseudo-labels, while the S-Net is a replaceable SOD network supervised by the pseudo labels generated by the current R-Net. Note that, we only need to use the trained S-Net for testing. Moreover, in order to guarantee the effectiveness and efficiency of network training, we design three training strategies, including alternate iteration mechanism, group-wise incremental mechanism, and credibility verification mechanism. Experiments on five SOD benchmarks show that our method achieves competitive performance against weakly-supervised/unsupervised methods both qualitatively and quantitatively. The code and results can be found from the link of https://rmcong.github.io/proj Hybrid-Label-SOD.html.
Original language | English |
---|---|
Pages (from-to) | 534-548 |
Number of pages | 15 |
Journal | IEEE Transactions on Circuits and Systems for Video Technology |
Volume | 33 |
Issue number | 2 |
Early online date | 8 Sept 2022 |
DOIs | |
Publication status | Published - Feb 2023 |
Externally published | Yes |
Bibliographical note
Funding Information:This work was supported in part by the National Key Research and Development Program of China under Grant 2021ZD0112100; in part by the Beijing Nova Program under Grant Z201100006820016; in part by the National Natural Science Foundation of China under Grant 62002014, Grant U1936212, and Grant 62120106009; in part by the Beijing Natural Science Foundation under Grant 4222013; in part by the Hong Kong Innovation and Technology Commission (InnoHK Project CIMDA); in part by the Hong Kong GRF-RGC General Research Fund under Grant 11209819 (CityU 9042816) and Grant 11203820 (CityU 9042598); in part by the Natural Science Foundation of Zhejiang under Grant LR22F020002; in part by the Young Elite Scientist Sponsorship Program by the China Association for Science and Technology under Grant 2020QNRC001; and in part by the CAAI-Huawei MindSpore Open Fund. The work of Runmin Cong was supported in part by the Fundamental Research Funds for the Central Universities under Grant 2022JBMC002.
Publisher Copyright:
© 1991-2012 IEEE.
Keywords
- blender
- group-wise incremental mechanism
- hybrid labels
- Salient object detection
- weakly supervised learning
Fingerprint
Dive into the research topics of 'A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels'. Together they form a unique fingerprint.Projects
- 1 Active
-
Adaptive Dynamic Range Enhancement Oriented to High Dynamic Display (面向高動態顯示的自適應動態範圍增強)
KWONG, S. T. W., KUO, C. J., WANG, S. & ZHANG, X.
Research Grants Council (HKSAR)
1/01/21 → 30/06/24
Project: Grant Research