Minhui Hu

Minhui Hu

Auto-generated profile, based on publicly available information

Minhui Hu

The 63rd Research Institute, National University of Defense Technology, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
26 January 2023 in Gut and Liver
Verified
Journal Article
Open access
PDF file
YLYi Lu
Yi Lu
JWJiachuan Wu
Jiachuan Wu
MHMinhui Hu
Minhui Hu
QZQinghua Zhong
Qinghua Zhong
LELimian Er
Limian Er
JSJiachen Sun
Jiachen Sun
Yi Lu, Jiachuan Wu, Minhui Hu, Qinghua Zhong, Limian Er, Huihui Shi, Weihui Cheng, Ke Chen, Yuan Liu, Bingfeng Qiu, Qiancheng Xu, Guangshun Lai, Yufeng Wang, Yuxuan Luo, Jinbao Mu, Wenjie Zhang, Min Zhi, and Jiachen Sun. Gut and Liver 2023;17:874-83. https://doi.org/10.5009/gnl220347

24 April 2021 in Entropy
Verified
Journal Article
Open access
PDF file
MHMinhui Hu
Minhui Hu
KZKaiwei Zeng
Kaiwei Zeng
YWYaohua Wang
Yaohua Wang
YGYang Guo
Yang Guo
Unsupervised domain adaptation is a challenging task in person re-identification (re-ID). Recently, cluster-based methods achieve good performance; clustering and training are two important phases in these methods. For clustering, one major issue of existing methods is that they do not fully exploit the information in outliers by either discarding outliers in clusters or simply merging outliers. For training, existing methods only use source features for pretraining and target features for fine-tuning and do not make full use of all valuable information in source datasets and target datasets. To solve these problems, we propose a Threshold-based Hierarchical clustering method with Contrastive loss (THC). There are two features of THC: (1) it regards outliers as single-sample clusters to participate in training. It well preserves the information in outliers without setting cluster number and combines advantages of existing clustering methods; (2) it uses contrastive loss to make full use of all valuable information, including source-class centroids, target-cluster centroids and single-sample clusters, thus achieving better performance. We conduct extensive experiments on Market-1501, DukeMTMC-reID and MSMT17. Results show our method achieves state of the art.

27 October 2023
Verified
Conference Paper
Open access
MHMinhui Hu
Minhui Hu
JFJianhua Fan
Jianhua Fan
GWGuanwu Wang
Guanwu Wang
YHYongyang Hu
Yongyang Hu
Unsupervised domain adaptation in person re-identification is a challenging task due to domain shifts between different datasets. Some cluster-based domain adaptation methods have made good progresses. However, most of these methods only focus on differences between global features while ignoring local features. In this paper, we propose a Patch and Cluster-based Domain adaptation (PCD) method. Specifically, we introduce the concept of patch-level local features and use spatial transformer to generate patches. We consider both global features (image-level) and local features (patch-level), so we get great accuracy. We evaluate our model on Market-1501 and DukeMTMC-reID. Extensive experiments show the efficiency of the method.

3 March 2022 in Journal of Circuits, Systems and Computers
Verified
Journal Article
Closed access
PDF file
JHJian Hu
Jian Hu
MHMinhui Hu
Minhui Hu
KZKuang Zhao
Kuang Zhao
YKYun Kang
Yun Kang
HYHaitao Yang
Haitao Yang
JCJie Cheng
Jie Cheng