Yaning Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yaning Han has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Fuxian Yu
Institute of Virology and Biotechnology, Zhejiang Academy of Agriculture Science, Hangzhou 310021, China
1 shared publication - Handan Zhang
Information Engineering College, Capital Normal University, China
1 shared publication - Hui Ding
Capital Normal University
1 shared publication J. Deng
South China University of Technology University, School of Electric Power, Guangzhou, China
1 shared publicationJ. Huang
South China University of Technology University, School of Electric Power, Guangzhou, China
1 shared publicationJ. Zhang
Energy Development Research Institute, CSG, China
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.
- 3 February 2022
- Published by Institution of Engineering and Technology (IET) in IET Conference Proceedings
- Vol. 2021 (9) , 170-176
Failure analysis of ZnO arresters in the 500kV AC filter of the HVDC/UHVDC power transmission system
The ZnO arresters in 500kV AC filters in many converter stations have abnormal discharge during operation, which accelerated the aging of arresters and even caused arresters out of work. In this paper, through the disassembly experiment of the whole arresters and the test of the electrical characteristic parameters of the varistors, the failure reason and aging characteristics are preliminarily analyzed. Firstly, it is found that there are obvious cracks and surface discharge traces on one individual varistor of the F1 arrester for AC filter; while disassembling the F2 arrester for AC filter, it is found that the appearance of the porcelain sleeve and the internal va ristors of the arrester are intact. Secondly, The electrical characteristic parameters measurement results show that the electrical characteristic parameters of each varistor of F1 arrester for AC filt er are dispersed, as high as 8%; the DC reference volta ge U1mA and leakage current IL at 0.75 times U1mA of each varistor of F2 arrester for AC filter have obvious polarity effect. Therefore, it is preliminarily inferred that the frequent large impulse current is the main reason of the arresters failure, and p arameters dispersion and polarity effect of the varistors in one arrester are critical influencing factors.
- 3 February 2022
- Published by Institution of Engineering and Technology (IET) in IET Conference Proceedings
- Vol. 2021 (9) , 170-176
Failure analysis of ZnO arresters in the 500kV AC filter of the HVDC/UHVDC power transmission system
The ZnO arresters in 500kV AC filters in many converter stations have abnormal discharge during operation, which accelerated the aging of arresters and even caused arresters out of work. In this paper, through the disassembly experiment of the whole arresters and the test of the electrical characteristic parameters of the varistors, the failure reason and aging characteristics are preliminarily analyzed. Firstly, it is found that there are obvious cracks and surface discharge traces on one individual varistor of the F1 arrester for AC filter; while disassembling the F2 arrester for AC filter, it is found that the appearance of the porcelain sleeve and the internal va ristors of the arrester are intact. Secondly, The electrical characteristic parameters measurement results show that the electrical characteristic parameters of each varistor of F1 arrester for AC filt er are dispersed, as high as 8%; the DC reference volta ge U1mA and leakage current IL at 0.75 times U1mA of each varistor of F2 arrester for AC filter have obvious polarity effect. Therefore, it is preliminarily inferred that the frequent large impulse current is the main reason of the arresters failure, and p arameters dispersion and polarity effect of the varistors in one arrester are critical influencing factors.