Wenbo Qi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wenbo Qi has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Shing Chow Chan
The University of Hong Kong
5 shared publications - Chengrong Yu
Yunnan University, Kunming, China
2 shared publications - Ho Chun Wu
Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong, China
2 shared publications - Jiafei Wu
Zhejiang University, Hangzhou, China
2 shared publications - Junjie Hu
College of Computer Science, Sichuan University, Chengdu, China
2 shared publications - Shengqian Zhu
Sichuan University, Chengdu, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16279-16287
Deconstructing Supervision: Rethinking Learning Signals in Class Incremental Medical Image Segmentation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16279-16287
Open AccessDeconstructing Supervision: Rethinking Learning Signals in Class Incremental Medical Image Segmentation
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 136711-136724
A Data- and Physical- Features Driven Graph Convolution Network for Explainable Prediction of Schizophrenia With Electroencephalography
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 136711-136724
Open AccessA Data- and Physical- Features Driven Graph Convolution Network for Explainable Prediction of Schizophrenia With Electroencephalography
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4688-4697
PRIME: Prototype-Driven Class Incremental Learning for Medical Image Segmentation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4688-4697
Open AccessPRIME: Prototype-Driven Class Incremental Learning for Medical Image Segmentation
- 27 November 2024
- Published by Springer Nature
- p. 473-490
Gradient-Aware for Class-Imbalanced Semi-supervised Medical Image Segmentation
- 27 November 2024
- Published by Springer Nature
- p. 473-490
Gradient-Aware for Class-Imbalanced Semi-supervised Medical Image Segmentation
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 4842-4855
MDF-Net: A Multi-Scale Dynamic Fusion Network for Breast Tumor Segmentation of Ultrasound Images
Breast tumor segmentation of ultrasound images provides valuable information of tumors for early detection and diagnosis. Accurate segmentation is challenging due to low image contrast between areas of interest; speckle noises, and large inter-subject variations in tumor shape and size. This paper proposes a novel Multi-scale Dynamic Fusion Network (MDF-Net) for breast ultrasound tumor segmentation. It employs a two-stage end-to-end architecture with a trunk sub-network for multiscale feature selection and a structurally optimized refinement sub-network for mitigating impairments such as noise and inter-subject variation via better feature exploration and fusion. The trunk network is extended from UNet++ with a simplified skip pathway structure to connect the features between adjacent scales. Moreover, deep supervision at all scales, instead of at the finest scale in UNet++, is proposed to extract more discriminative features and mitigate errors from speckle noise via a hybrid loss function. Unlike previous works, the first stage is linked to a loss function of the second stage so that both the preliminary segmentations and refinement subnetworks can be refined together at training. The refinement sub-network utilizes a structurally optimized MDF mechanism to integrate preliminary segmentation information (capturing general tumor shape and size) at coarse scales and explores inter-subject variation information at finer scales. Experimental results from two public datasets show that the proposed method achieves better Dice and other scores over state-of-the-art methods. Qualitative analysis also indicates that our proposed network is more robust to tumor size/shapes, speckle noise and heavy posterior shadows along tumor boundaries. An optional post-processing step is also proposed to facilitate users in mitigating segmentation artifacts. The efficiency of the proposed network is also illustrated on the “Electron Microscopy neural structures segmentation dataset”. It outperforms a state-of-the-art algorithm based on UNet-2022 with simpler settings. This indicates the advantages of our MDF-Nets in other challenging image segmentation tasks with small to medium data sizes.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 4842-4855
MDF-Net: A Multi-Scale Dynamic Fusion Network for Breast Tumor Segmentation of Ultrasound Images
Breast tumor segmentation of ultrasound images provides valuable information of tumors for early detection and diagnosis. Accurate segmentation is challenging due to low image contrast between areas of interest; speckle noises, and large inter-subject variations in tumor shape and size. This paper proposes a novel Multi-scale Dynamic Fusion Network (MDF-Net) for breast ultrasound tumor segmentation. It employs a two-stage end-to-end architecture with a trunk sub-network for multiscale feature selection and a structurally optimized refinement sub-network for mitigating impairments such as noise and inter-subject variation via better feature exploration and fusion. The trunk network is extended from UNet++ with a simplified skip pathway structure to connect the features between adjacent scales. Moreover, deep supervision at all scales, instead of at the finest scale in UNet++, is proposed to extract more discriminative features and mitigate errors from speckle noise via a hybrid loss function. Unlike previous works, the first stage is linked to a loss function of the second stage so that both the preliminary segmentations and refinement subnetworks can be refined together at training. The refinement sub-network utilizes a structurally optimized MDF mechanism to integrate preliminary segmentation information (capturing general tumor shape and size) at coarse scales and explores inter-subject variation information at finer scales. Experimental results from two public datasets show that the proposed method achieves better Dice and other scores over state-of-the-art methods. Qualitative analysis also indicates that our proposed network is more robust to tumor size/shapes, speckle noise and heavy posterior shadows along tumor boundaries. An optional post-processing step is also proposed to facilitate users in mitigating segmentation artifacts. The efficiency of the proposed network is also illustrated on the “Electron Microscopy neural structures segmentation dataset”. It outperforms a state-of-the-art algorithm based on UNet-2022 with simpler settings. This indicates the advantages of our MDF-Nets in other challenging image segmentation tasks with small to medium data sizes.
- Open Access
- 26 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 115826-115838
A Color/Illuminance Aware Data Augmentation and Style Adaptation Approach to Person Re-Identification
Person re-identification problems usually suffer from large subject appearance variations and limited training data. This paper proposes a novel physically motivated Color/Illuminance-Aware data-augmentation (CIADA) scheme and a style-adaptive fusion approach to address these issues. The CIADA scheme estimates the color/illuminance distribution from the training data via manifold learning and generates new samples under different color/illuminance perturbations to better capture objects’ appearance for mitigating the small-sample-size and color variation problems. A Color/Illuminance Aware Feature Augmentation (CIAFA) approach, which is applicable to state-of-the-art features and metric learning algorithms, is then proposed to integrate the features generated by the augmented samples for metric learning. A new Color/Illuminance-Aware Style Fusion (CIASF) scheme, which allows the learning and matching process to be performed independently on each pair of datasets generated for estimating a set of ‘local’ distance functions, is also proposed. A canonical correlation analysis-based weighting scheme is developed to fuse these local distances to an overall distance for recognition. This reduces the memory requirement and complexity over the original CIAFA. Experiments on common datasets show that the proposed methodologies substantially improve the performance of state-of-the-art subspace learning algorithms. It is applicable to both small and large datasets with hand-craft and deep features.
- 26 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 115826-115838
Open AccessA Color/Illuminance Aware Data Augmentation and Style Adaptation Approach to Person Re-Identification
Person re-identification problems usually suffer from large subject appearance variations and limited training data. This paper proposes a novel physically motivated Color/Illuminance-Aware data-augmentation (CIADA) scheme and a style-adaptive fusion approach to address these issues. The CIADA scheme estimates the color/illuminance distribution from the training data via manifold learning and generates new samples under different color/illuminance perturbations to better capture objects’ appearance for mitigating the small-sample-size and color variation problems. A Color/Illuminance Aware Feature Augmentation (CIAFA) approach, which is applicable to state-of-the-art features and metric learning algorithms, is then proposed to integrate the features generated by the augmented samples for metric learning. A new Color/Illuminance-Aware Style Fusion (CIASF) scheme, which allows the learning and matching process to be performed independently on each pair of datasets generated for estimating a set of ‘local’ distance functions, is also proposed. A canonical correlation analysis-based weighting scheme is developed to fuse these local distances to an overall distance for recognition. This reduces the memory requirement and complexity over the original CIAFA. Experiments on common datasets show that the proposed methodologies substantially improve the performance of state-of-the-art subspace learning algorithms. It is applicable to both small and large datasets with hand-craft and deep features.