Chaohong Tan
Chaohong Tan has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Baohua Huang
School of Computer and Electronic Information, Guangxi University, Nanning 530004, China
1 shared publication - Fanchao Li
College of Computer, Electronic and Information, Guangxi University, Nanning, China
1 shared publication - Han Sun
School of Computer and Electronic Information, Guangxi University, Nanning 530004, China
1 shared publication - Hancheng Wang
Guangxi Key Laboratory of Digital Infrastructure, Guangxi Zhuang Autonomous Region Information Center, Nanning 530000, China
1 shared publication - Jie Qin
School of Computer Science and Electronic Engineering, Guangxi University, Nanning 530004, China
1 shared publication - Si Pang
School of Computer and Electronic Information, Guangxi University, Nanning 530004, China
1 shared publication
Latest Publications
- Open Access
- 1 May 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (6)
Class-disentangled attribution with gradient guidance for CLIP
Large-scale vision–language pre-trained models such as CLIP play a central role in modern multimodal artificial intelligence. However, their cross-modal decision process remains difficult to interpret, which limits reliable deployment in practical applications. Existing explanation methods for CLIP often exhibit semantic entanglement and inaccurate spatial localization in cross-modal attribution. This paper presents a gradient-guided class-aware semantic disentanglement attribution method for CLIP. The proposed method explicitly disentangles class-related semantics aggregated in the global token during attribution. This design suppresses irrelevant semantic interference and produces visual explanations with improved semantic consistency, clearer structural organization, and more accurate spatial localization. We further introduce a novel gradient guidance strategy that balances importance assignment at the channel level and guides spatial attribution toward regions that are discriminative for the target semantics. As a result, the proposed approach generates more stable and faithful visual explanations. Extensive qualitative and quantitative experiments on ImageNet and MSCOCO 2014 demonstrate that the proposed method consistently outperforms existing approaches in explanation fidelity and reliability.
- 1 May 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (6)
Open AccessClass-disentangled attribution with gradient guidance for CLIP
Large-scale vision–language pre-trained models such as CLIP play a central role in modern multimodal artificial intelligence. However, their cross-modal decision process remains difficult to interpret, which limits reliable deployment in practical applications. Existing explanation methods for CLIP often exhibit semantic entanglement and inaccurate spatial localization in cross-modal attribution. This paper presents a gradient-guided class-aware semantic disentanglement attribution method for CLIP. The proposed method explicitly disentangles class-related semantics aggregated in the global token during attribution. This design suppresses irrelevant semantic interference and produces visual explanations with improved semantic consistency, clearer structural organization, and more accurate spatial localization. We further introduce a novel gradient guidance strategy that balances importance assignment at the channel level and guides spatial attribution toward regions that are discriminative for the target semantics. As a result, the proposed approach generates more stable and faithful visual explanations. Extensive qualitative and quantitative experiments on ImageNet and MSCOCO 2014 demonstrate that the proposed method consistently outperforms existing approaches in explanation fidelity and reliability.
- Open Access
- 19 August 2024
- Published by MDPI AG in Electronics
- Vol. 13 (16) , 3277
A UAV Aerial Image Target Detection Algorithm Based on YOLOv7 Improved Model
To address the challenges of multi-scale objects, dense distributions, occlusions, and numerous small targets in UAV image detection, we present CMS-YOLOv7, a real-time target detection method based on an enhanced YOLOv7 model. Firstly, the detection layer P2 for small targets was added to YOLOv7 to enhance the detection ability of small and medium-sized targets, and the deep detection head P5 was taken out to mitigate the influence of excessive downsampling on small target images. The anchor frame was calculated by the K-means++ method. Using the concept of Inner-IoU, the Inner-MPDIoU loss function was constructed to control the range of the auxiliary border and improve detection performance. Furthermore, the CARAFE module was introduced to replace traditional upsampling methods, offering improved integration of semantic information during the image upsampling process and enhancing feature mapping accuracy. Simultaneously, during the feature extraction stage, a non-strided convolutional SPD-Conv module was constructed using space-to-depth techniques. This module replaced certain convolutional operations to minimize the loss of fine-grained information and improve the model’s ability to extract features from small targets. Experiments on the UAV aerial photo dataset VisDrone2019 demonstrated that compared with the baseline YOLOv7 object detection algorithm, CMS-YOLOv7 achieved an improvement of 3.5% mAP@0.5, 3.0% mAP@0.5:0.95, and the number of parameters decreased by 18.54 M. The ability of small target detection was significantly enhanced.
- 19 August 2024
- Published by MDPI AG in Electronics
- Vol. 13 (16) , 3277
Open AccessA UAV Aerial Image Target Detection Algorithm Based on YOLOv7 Improved Model
To address the challenges of multi-scale objects, dense distributions, occlusions, and numerous small targets in UAV image detection, we present CMS-YOLOv7, a real-time target detection method based on an enhanced YOLOv7 model. Firstly, the detection layer P2 for small targets was added to YOLOv7 to enhance the detection ability of small and medium-sized targets, and the deep detection head P5 was taken out to mitigate the influence of excessive downsampling on small target images. The anchor frame was calculated by the K-means++ method. Using the concept of Inner-IoU, the Inner-MPDIoU loss function was constructed to control the range of the auxiliary border and improve detection performance. Furthermore, the CARAFE module was introduced to replace traditional upsampling methods, offering improved integration of semantic information during the image upsampling process and enhancing feature mapping accuracy. Simultaneously, during the feature extraction stage, a non-strided convolutional SPD-Conv module was constructed using space-to-depth techniques. This module replaced certain convolutional operations to minimize the loss of fine-grained information and improve the model’s ability to extract features from small targets. Experiments on the UAV aerial photo dataset VisDrone2019 demonstrated that compared with the baseline YOLOv7 object detection algorithm, CMS-YOLOv7 achieved an improvement of 3.5% mAP@0.5, 3.0% mAP@0.5:0.95, and the number of parameters decreased by 18.54 M. The ability of small target detection was significantly enhanced.
- Open Access
- 30 July 2024
- Published by MDPI AG in Electronics
- Vol. 13 (15) , 3001
RA-YOLOv8: An Improved YOLOv8 Seal Text Detection Method
To detect text from electronic seals that have significant background interference, blurring, text overlapping, and curving, an improved YOLOv8 model named RA-YOLOv8 was developed. The model is primarily based on YOLOv8, with optimized structures in its backbone and neck. The receptive-field attention and efficient multi-scale attention (RFEMA) module is introduced in the backbone. The model’s ability to extract and integrate local and global features is enhanced by combining the attention on the receptive-field spatial feature of the receptive-field attention and coordinate attention (RFCA) module and the cross-spatial learning of the efficient multi-scale attention (EMA) module. The Alterable Kernel Convolution (AKConv) module is incorporated in the neck, enhancing the model’s detection accuracy of curved text by dynamically adjusting the sampling position. Furthermore, to boost the model’s detection performance, the original loss function is replaced with the bounding box regression loss function of Minimum Point Distance Intersection over Union (MPDIoU). Experimental results demonstrate that RA-YOLOv8 surpasses YOLOv8 in terms of precision, recall, and F1 value, with improvements of 0.4%, 1.6%, and 1.03%, respectively, validating its effectiveness and utility in seal text detection.
- 30 July 2024
- Published by MDPI AG in Electronics
- Vol. 13 (15) , 3001
Open AccessRA-YOLOv8: An Improved YOLOv8 Seal Text Detection Method
To detect text from electronic seals that have significant background interference, blurring, text overlapping, and curving, an improved YOLOv8 model named RA-YOLOv8 was developed. The model is primarily based on YOLOv8, with optimized structures in its backbone and neck. The receptive-field attention and efficient multi-scale attention (RFEMA) module is introduced in the backbone. The model’s ability to extract and integrate local and global features is enhanced by combining the attention on the receptive-field spatial feature of the receptive-field attention and coordinate attention (RFCA) module and the cross-spatial learning of the efficient multi-scale attention (EMA) module. The Alterable Kernel Convolution (AKConv) module is incorporated in the neck, enhancing the model’s detection accuracy of curved text by dynamically adjusting the sampling position. Furthermore, to boost the model’s detection performance, the original loss function is replaced with the bounding box regression loss function of Minimum Point Distance Intersection over Union (MPDIoU). Experimental results demonstrate that RA-YOLOv8 surpasses YOLOv8 in terms of precision, recall, and F1 value, with improvements of 0.4%, 1.6%, and 1.03%, respectively, validating its effectiveness and utility in seal text detection.