Yun Wang

Yun Wang

Auto-generated profile, based on publicly available information

Yun Wang

School of Information Engineering, East China Jiaotong University, Nanchang, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YWYun Wang
Yun Wang
LZLu Zhu
Lu Zhu
YLYuanyuan Liu
Yuanyuan Liu
Few-shot semantic segmentation aims to extract information from few annotated support images to segment unknown class objects in the query image. Traditional algorithms may produce errors and insufficient feature extraction using multi-layer cosine similarity to extract correlation information, due to the large differences in appearance and posture between novel class objects, as well as the similarity in texture and shape among different categories. To address the above issue, we propose a Complementary Feature-Enhanced Network (CFENet). Specifically, we propose a correlation complementary extraction module (CCEM) to facilitate long-range information interaction between query features and support features in the intermediate layer, which contains detailed information. The generated multichannel correlation information complements the prior information obtained through cosine similarity comparison. In addition, we propose a multi-branch feature enhancement module to capture long-range dependencies in aggregated features which are composed of prior correlation information and query features. The module effectively suppresses noise in the aggregated features and enhances the query target object feature from both global and local perspectives in a complementary way. Experiments of the network on PASCAL-5 i and COCO-20 i datasets validate the effectiveness of our proposed method. The source code is available at https://github.com/wangyunXL/CFENet

1 October 2018
Verified
Conference Paper
Closed access
XJXiaoxuan Jiao
Xiaoxuan Jiao
BJBo Jing
Bo Jing
BJBeiquan Jiao
Beiquan Jiao
SSShuhao Si
Shuhao Si
YWYun Wang
Yun Wang
The problem of selecting optimal sensors is a typical discrete combinatorial optimization problem, which is proved to be NP-hard. In this paper, an improved binary wolf pack algorithm (IBWPA) by adaptive step length, information interaction and difference evolution update strategy is proposed to choose the optimal sensors with high computational accuracy and robustness. Firstly, the wolves' position, motion operator, intelligent behaviors and rules of basic binary wolf algorithm for optimum in discrete state space are introduced. Then, tentative direction of scouting behavior based on information interaction, adaptive steps length of scouting and summoning behavior, as well as the differential evolution updates strategy are used to improve the traditional BWPA and the schemes and procedures of IBWPA are also presented. Finally, experiments show that compared with BPSO, BWPA and other sensor selection methods, the proposed IBWPA method has a better accuracy, robustness and global searching ability and the problem can be solved in reasonable computational time. Moreover, the effects of algorithm parameters on the performance of selecting optimum are also analyzed through simulation and theoretical analysis, which indicate that IBWPA can achieve a better tradeoff between the global searching ability and computational time by choosing reasonable parameters.