A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels

作者：Cong, Runmin; Qin, Qi; Zhang, Chen^*; Jiang, Qiuping; Wang, Shiqi; Zhao, Yao; Kwong, Sam

来源：IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(2): 534-548.

DOI：10.1109/TCSVT.2022.3205182

• |Salient object detection
• weakly supervised learning
• hybrid labels
• blender
• group-wise incremental mechanism

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.

• 单位
  北京交通大学