Wei-Ping Ma
Wei-Ping Ma has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Peng-Xia Cao
Lanzhou Institute of Physics, China Academy of Space Technology, Lanzhou, China
4 shared publications - Wen-Xin Li
Lanzhou Institute of Physics, China Academy of Space Technology, Lanzhou, China
4 shared publications - Jin-Chuan Sun
Lanzhou Institute of Physics, China Academy of Space Technology, Lanzhou, China
1 shared publication
Latest Publications
- Open Access
- 30 June 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (6) , e0352358
Dual cross-attentive mutual teaching for semi-supervised 3D medical segmentation
Semi-supervised learning can reduce the dependence on large-scale labeled data in 3D medical image segmentation.In this work, we propose a new Dual Crossed Attention Mutual Teaching (DCA-MT) framework that effectively utilizes both labeled and unlabeled data by integrating high-dimensional feature alignment, semantic-level crossed attention, and bidirectional knowledge distillation. Specifically, we employ a two-branch VNet architecture where the teacher-student network co-evolves through mutual mentoring and collaborative learning.To enhance representation consistency, we introduce maximum mean difference (MMD) loss and inter-class and intra-class contrast constraints to achieve global feature distribution alignment and class-level separability. A multi-head cross-attention module is designed to facilitate fine-grained semantic interaction between the two networks, allowing the two branches to dynamically exchange complementary features.In addition, the two-way mutual distillation strategy ensures that teacher and student networks benefit from each other's knowledge. Numerous experiments on the left atrial and pancreatic nih datasets show that our proposed approach has better performance and verifies the effectiveness and robustness of DCA-MT.
- 30 June 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (6) , e0352358
Open AccessDual cross-attentive mutual teaching for semi-supervised 3D medical segmentation
Semi-supervised learning can reduce the dependence on large-scale labeled data in 3D medical image segmentation.In this work, we propose a new Dual Crossed Attention Mutual Teaching (DCA-MT) framework that effectively utilizes both labeled and unlabeled data by integrating high-dimensional feature alignment, semantic-level crossed attention, and bidirectional knowledge distillation. Specifically, we employ a two-branch VNet architecture where the teacher-student network co-evolves through mutual mentoring and collaborative learning.To enhance representation consistency, we introduce maximum mean difference (MMD) loss and inter-class and intra-class contrast constraints to achieve global feature distribution alignment and class-level separability. A multi-head cross-attention module is designed to facilitate fine-grained semantic interaction between the two networks, allowing the two branches to dynamically exchange complementary features.In addition, the two-way mutual distillation strategy ensures that teacher and student networks benefit from each other's knowledge. Numerous experiments on the left atrial and pancreatic nih datasets show that our proposed approach has better performance and verifies the effectiveness and robustness of DCA-MT.
- Open Access
- 23 January 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (1) , e0340765
Study on salient object segmentation based on depth information guidance and SAM low-rank adaptation fine-tuning
Accurate segmentation of salient objects is crucial for various computer vision applications including image editing, autonomous driving, and object detection. While research on using depth information (RGB-D) in saliency detection is gaining significant attention, its broad application is limited by dependencies on depth sensors and the challenge of effectively integrating RGB and depth information. To address these issues, we propose an innovative method for salient object segmentation that integrates the Segment Anything Model (SAM), depth information, and cross-modal attention mechanisms. Our approach leverages SAM for robust feature extraction and combines it with a pre-trained depth estimation network to capture geometric information. By dynamically fusing features from RGB and depth modalities through a cross-modal attention mechanism, our method enhances the ability to handle diverse scenes. Additionally, we achieve computational efficiency without compromising precision by employing lightweight LoRA fine-tuning and freezing pre-trained weights. The use of a UNet decoder refines the segmentation output, ensuring the preservation of target boundary details in high-resolution outputs. Experiments conducted on five challenging benchmark datasets validate the effectiveness of our proposed method. Results show significant improvements over existing methods across key evaluation metrics, including MaxF, MAE, and S-measure. Particularly in tasks involving complex backgrounds, small targets, and multiple salient object segmentation, our method demonstrates superior performance and robustness. The significance of this work lies in advancing the application of depth-guided RGB in salient object segmentation while offering new insights into overcoming depth sensor dependency. Furthermore, it opens up novel pathways for the effective fusion of cross-modal information, thereby contributing to the broader development and diversification of related technologies and their applications.
- 23 January 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (1) , e0340765
Open AccessStudy on salient object segmentation based on depth information guidance and SAM low-rank adaptation fine-tuning
Accurate segmentation of salient objects is crucial for various computer vision applications including image editing, autonomous driving, and object detection. While research on using depth information (RGB-D) in saliency detection is gaining significant attention, its broad application is limited by dependencies on depth sensors and the challenge of effectively integrating RGB and depth information. To address these issues, we propose an innovative method for salient object segmentation that integrates the Segment Anything Model (SAM), depth information, and cross-modal attention mechanisms. Our approach leverages SAM for robust feature extraction and combines it with a pre-trained depth estimation network to capture geometric information. By dynamically fusing features from RGB and depth modalities through a cross-modal attention mechanism, our method enhances the ability to handle diverse scenes. Additionally, we achieve computational efficiency without compromising precision by employing lightweight LoRA fine-tuning and freezing pre-trained weights. The use of a UNet decoder refines the segmentation output, ensuring the preservation of target boundary details in high-resolution outputs. Experiments conducted on five challenging benchmark datasets validate the effectiveness of our proposed method. Results show significant improvements over existing methods across key evaluation metrics, including MaxF, MAE, and S-measure. Particularly in tasks involving complex backgrounds, small targets, and multiple salient object segmentation, our method demonstrates superior performance and robustness. The significance of this work lies in advancing the application of depth-guided RGB in salient object segmentation while offering new insights into overcoming depth sensor dependency. Furthermore, it opens up novel pathways for the effective fusion of cross-modal information, thereby contributing to the broader development and diversification of related technologies and their applications.
- 30 January 2021
- Published by Springer Nature in International Journal of Automation and Computing
- Vol. 18 (2) , 288-299
A Tracking Registration Method for Augmented Reality Based on Multi-modal Template Matching and Point Clouds
- 30 January 2021
- Published by Springer Nature in International Journal of Automation and Computing
- Vol. 18 (2) , 288-299
A Tracking Registration Method for Augmented Reality Based on Multi-modal Template Matching and Point Clouds
- 21 October 2020
- Published by Springer Nature in International Journal of Automation and Computing
- Vol. 18 (1) , 73-84
Saliency Detection via Manifold Ranking Based on Robust Foreground
- 21 October 2020
- Published by Springer Nature in International Journal of Automation and Computing
- Vol. 18 (1) , 73-84
Saliency Detection via Manifold Ranking Based on Robust Foreground
- 1 April 2020
- Published by Springer Nature in International Journal of Automation and Computing
- Vol. 17 (4) , 562-571
Binocular Vision Object Positioning Method for Robots Based on Coarse-fine Stereo Matching
- 1 April 2020
- Published by Springer Nature in International Journal of Automation and Computing
- Vol. 17 (4) , 562-571
Binocular Vision Object Positioning Method for Robots Based on Coarse-fine Stereo Matching
- Open Access
- 9 July 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 252 (2) , 022149
Ranging Method of Binocular Stereo Vision Based on Random Ferns and NCC Template Matching
As an important research direction in the field of computer vision, binocular stereo vision has important application value for the reconstruction of scene 3D geometric information. A fast and accurate binocular vision target ranging method is proposed. Firstly, the random fern algorithm is used to accurately and quickly detect the left image target area to obtain the target center point. Then the NCC template matching algorithm is used to find the matching point in the right image. Finally, the two-dimensional coordinates of the matching point pairs of center point is used to calculate the distance between the target and the camera. The simulation results show that the ranging scheme can accurately measure the target distance within a certain distance range, and can achieve fast and effective target ranging.
- 9 July 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 252 (2) , 022149
Open AccessRanging Method of Binocular Stereo Vision Based on Random Ferns and NCC Template Matching
As an important research direction in the field of computer vision, binocular stereo vision has important application value for the reconstruction of scene 3D geometric information. A fast and accurate binocular vision target ranging method is proposed. Firstly, the random fern algorithm is used to accurately and quickly detect the left image target area to obtain the target center point. Then the NCC template matching algorithm is used to find the matching point in the right image. Finally, the two-dimensional coordinates of the matching point pairs of center point is used to calculate the distance between the target and the camera. The simulation results show that the ranging scheme can accurately measure the target distance within a certain distance range, and can achieve fast and effective target ranging.