Mingwei Hu

Mingwei Hu

Auto-generated profile, based on publicly available information

Mingwei Hu

Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education, School of Artificial Intelligence, Xidian University, Xian, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
4 December 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
WZWeitong Zhang
Weitong Zhang
MHMingwei Hu
Mingwei Hu
SHSihan Hou
Sihan Hou
Ronghua ShangRonghua Shang
Ronghua Shang
JFJie Feng
Jie Feng
SXSonghua Xu
Songhua Xu

26 December 2024 in Applied Soft Computing
Verified
Journal Article
Closed access
RSRonghua Shang
Ronghua Shang
MHMingwei Hu
Mingwei Hu
JFJie Feng
Jie Feng
WZWeitong Zhang
Weitong Zhang
SXSonghua Xu
Songhua Xu

23 May 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Ronghua ShangRonghua Shang
Ronghua Shang
MHMingwei Hu
Mingwei Hu
WLWenzheng Li
Wenzheng Li
LLLei Liu
Lei Liu
WZWeitong Zhang
Weitong Zhang
SXSonghua Xu
Songhua Xu
The models currently used for polarimetric synthetic aperture radar (PolSAR) image classification tasks have problems, such as complex network structures, poor distinction of detailed features, and fixed loss weights during the training process. In response to these problems, this article proposes a PolSAR image classification method based on knowledge distillation using adaptive learning and channel amplification features. First, this article builds a knowledge distillation framework for PolSAR. Using a teacher network trained in advance that can acquire global knowledge to guide the student. This framework reduces the computational complexity and improves the classification accuracy of the student. Then, an adaptive loss weight learning mechanism is designed, which sets the weight of the Kullback-Leibler (KL) divergence loss during training into a learnable mode. The weight can be automatically adjusted according to the actual training situation of the student. Finally, a scheme for channel amplification to enhance features is proposed. This scheme obtains channel weights based on the student’s feature map information. These weights are amplified, strengthening the network’s ability to obtain feature information. Compared with the five PolSAR image classification algorithms, the method proposed in this article uses lower computational complexity to obtain higher classification accuracy on the Flevoland, San Francisco, and Xi’an datasets.

15 October 2025 in Applied Soft Computing
Verified
Journal Article
Closed access
JRJinhong Ren
Jinhong Ren
KZKeyao Zhu
Keyao Zhu
MHMingwei Hu
Mingwei Hu
Ronghua ShangRonghua Shang
Ronghua Shang
MZMengxuan Zhang
Mengxuan Zhang

15 October 2025 in Applied Soft Computing
Verified
Journal Article
Closed access
Ronghua ShangRonghua Shang
Ronghua Shang
MHMingwei Hu
Mingwei Hu
KZKeyao Zhu
Keyao Zhu
JRJinhong Ren
Jinhong Ren
Jie FengJie Feng
Jie Feng