Hong Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hong Zhao has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Zhaobin Chang
School of Information Science and Engineering, Lanzhou University, Lanzhou, China
7 shared publications - Dailin Huang
School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China
5 shared publications Weijie Wang
4 shared publicationsZhaobin Chang
4 shared publicationsJie Cao
3 shared publications- Weijie Wang
School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China
3 shared publications
Latest Publications
- 10 November 2026
- Published by Elsevier in Information Fusion
EVGNet: Efficient Visual Guardrails for Few-Shot Medical Image Segmentation
- 10 November 2026
- Published by Elsevier in Information Fusion
EVGNet: Efficient Visual Guardrails for Few-Shot Medical Image Segmentation
- Open Access
- 24 April 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3761
A review of the evolution and challenges of few-shot medical image semantic segmentation
Image segmentation, as a fundamental task in computer vision, aims to achieve pixel-level delineation between target regions and background. In the field of medical image analysis, traditional segmentation methods heavily rely on large-scale, high-quality annotated datasets. However, expert-level annotations for medical images require substantial professional human resources ( e.g ., radiologists performing slice-by-slice delineation of lesions) and face challenges such as cross-institutional data heterogeneity. To address this data bottleneck, few-shot medical image semantic segmentation has emerged as a promising paradigm. By leveraging strategies such as meta-learning, metric learning, and other related approaches, these approaches enable models to accurately segment the target region and achieve effective generalization to novel categories using minimal annotated samples (typically ≤15 instances per class), thereby significantly reducing dependence on annotated data. This article systematically explores foundational concepts such as medical image segmentation methods, benchmark datasets, performance evaluation metrics, and main approaches for few-shot medical image segmentation. Distinct from existing review literature, our work focuses on summarizing prototype-based few-shot medical image semantic segmentation algorithms. We analyze network architectures from a problem-oriented perspective and critically examine limitations in current methodologies. Finally, grounded in our analysis of current challenges, we propose forward-looking perspectives for future advancements.
- 24 April 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3761
Open AccessA review of the evolution and challenges of few-shot medical image semantic segmentation
Image segmentation, as a fundamental task in computer vision, aims to achieve pixel-level delineation between target regions and background. In the field of medical image analysis, traditional segmentation methods heavily rely on large-scale, high-quality annotated datasets. However, expert-level annotations for medical images require substantial professional human resources ( e.g ., radiologists performing slice-by-slice delineation of lesions) and face challenges such as cross-institutional data heterogeneity. To address this data bottleneck, few-shot medical image semantic segmentation has emerged as a promising paradigm. By leveraging strategies such as meta-learning, metric learning, and other related approaches, these approaches enable models to accurately segment the target region and achieve effective generalization to novel categories using minimal annotated samples (typically ≤15 instances per class), thereby significantly reducing dependence on annotated data. This article systematically explores foundational concepts such as medical image segmentation methods, benchmark datasets, performance evaluation metrics, and main approaches for few-shot medical image segmentation. Distinct from existing review literature, our work focuses on summarizing prototype-based few-shot medical image semantic segmentation algorithms. We analyze network architectures from a problem-oriented perspective and critically examine limitations in current methodologies. Finally, grounded in our analysis of current challenges, we propose forward-looking perspectives for future advancements.
- 6 December 2025
- Published by Elsevier in Neural Networks
- Vol. 196, 108409
Heterogeneous Feature Knowledge Distillation based on Enhanced Feature Projector Correlation
- 6 December 2025
- Published by Elsevier in Neural Networks
- Vol. 196, 108409
Heterogeneous Feature Knowledge Distillation based on Enhanced Feature Projector Correlation
- 1 October 2025
- Published by Elsevier in Neurocomputing
- Vol. 658
Generalizable 3D Gaussian splatting via multi-view stereo and consistency constraints
- 1 October 2025
- Published by Elsevier in Neurocomputing
- Vol. 658
Generalizable 3D Gaussian splatting via multi-view stereo and consistency constraints
- 3 December 2024
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 200
A deep reinforcement learning method based on a multiexpert graph neural network for flexible job shop scheduling
- 3 December 2024
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 200
A deep reinforcement learning method based on a multiexpert graph neural network for flexible job shop scheduling
- 20 November 2024
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 121
High frequency domain enhancement and channel attention module for multi-view stereo
- 20 November 2024
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 121
High frequency domain enhancement and channel attention module for multi-view stereo
- 5 November 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (6) , 1-17
Collaborative multi-knowledge distillation under the influence of softmax regression representation
- 5 November 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (6) , 1-17
Collaborative multi-knowledge distillation under the influence of softmax regression representation
- Open Access
- 17 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 168894-168903
MCA2Net-HFG: Handwritten Font Generation Based on Res2Net and Multi-Spectral Channel Attention
To address the issue of insufficient feature extraction in handwritten font generation models concerning stroke position, tilt angle, and stroke thickness, which leads to significant discrepancies in details between generated fonts and real handwritten fonts, we propose a handwritten font generation model, MCA2Net-HFG. The model is based on Residual Resolution Network(Res2Net) and Multi-spectral Channel Attention (MCA) as the main structure of the encoder. We use Res2Net as the backbone network of the Convolutional Neural Networks(CNN) encoder to capture font features at different scales, such as stroke thickness, curvature, and position, as well as other fine-grained characteristics. Additionally, incorporating Multi-spectral Channel Attention into Res2Net captures key feature information located at different frequencies within the channels, enabling the model to better learn important characteristics of fonts during the training phase. This ensures the authenticity of the generated handwritten fonts. Experimental results on the IAM dataset show that compared to the current best methods, MCA2Net-HFG reduces the Fréchet Inception Distance(FID) score by 18.60% and the Geometry Score(GS) score by 50.59%. This indicates that MCA2Net-HFG generates higher quality handwritten fonts and has greater practical value. Additionally, results on different test sets validate the model’s good generalization performance.
- 17 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 168894-168903
Open AccessMCA2Net-HFG: Handwritten Font Generation Based on Res2Net and Multi-Spectral Channel Attention
To address the issue of insufficient feature extraction in handwritten font generation models concerning stroke position, tilt angle, and stroke thickness, which leads to significant discrepancies in details between generated fonts and real handwritten fonts, we propose a handwritten font generation model, MCA2Net-HFG. The model is based on Residual Resolution Network(Res2Net) and Multi-spectral Channel Attention (MCA) as the main structure of the encoder. We use Res2Net as the backbone network of the Convolutional Neural Networks(CNN) encoder to capture font features at different scales, such as stroke thickness, curvature, and position, as well as other fine-grained characteristics. Additionally, incorporating Multi-spectral Channel Attention into Res2Net captures key feature information located at different frequencies within the channels, enabling the model to better learn important characteristics of fonts during the training phase. This ensures the authenticity of the generated handwritten fonts. Experimental results on the IAM dataset show that compared to the current best methods, MCA2Net-HFG reduces the Fréchet Inception Distance(FID) score by 18.60% and the Geometry Score(GS) score by 50.59%. This indicates that MCA2Net-HFG generates higher quality handwritten fonts and has greater practical value. Additionally, results on different test sets validate the model’s good generalization performance.