Handan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Handan Zhang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Hui Ding
Capital Normal University
1 shared publication - Tie Liu
Capital Normal University
1 shared publication - Yaning Han
Information Engineering College, Capital Normal University, China
1 shared publication - Yuanyuan Shang
Capital Normal University
1 shared publication - Zhuhong Shao
Capital Normal University
1 shared publication
Latest Publications
- Open Access
- 19 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Pseudo-labels Learning for Multi-source Weakly Supervised Salient Object Detection
Salient object detection based on weakly supervised learning has become an attractive direction because of high cost of pixel-level labels, but the information provided by a single weakly supervised source makes it difficult to train a well-performance model. In this paper, we propose a pseudo-labels learning method that is designed as a unified two-stage framework for multi-source weakly supervised salient object detection. In the first stage, we introduce a two-branch network to learn category labels and bounding boxes respectively. The first branch is the classification network to obtain class activation maps, and the other branch is based on bounding boxes training to generate salient bounding box attributed maps. Then, we propose an aggregation module, which fuses the maps generated by the above two branches and then refines them to get pixel-level pseudo-labels. In the second stage, we train the transformer model to predict salient maps using the final pseudo-labels as ground-truth. The proposed method is compared with existing methods on six datasets, and experimental results verify the effectiveness of our method.
- 19 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessPseudo-labels Learning for Multi-source Weakly Supervised Salient Object Detection
Salient object detection based on weakly supervised learning has become an attractive direction because of high cost of pixel-level labels, but the information provided by a single weakly supervised source makes it difficult to train a well-performance model. In this paper, we propose a pseudo-labels learning method that is designed as a unified two-stage framework for multi-source weakly supervised salient object detection. In the first stage, we introduce a two-branch network to learn category labels and bounding boxes respectively. The first branch is the classification network to obtain class activation maps, and the other branch is based on bounding boxes training to generate salient bounding box attributed maps. Then, we propose an aggregation module, which fuses the maps generated by the above two branches and then refines them to get pixel-level pseudo-labels. In the second stage, we train the transformer model to predict salient maps using the final pseudo-labels as ground-truth. The proposed method is compared with existing methods on six datasets, and experimental results verify the effectiveness of our method.