Zihao Guo; Mingwen Shao; Shunhang Li. Image-to-image translation using an offset-based multi-scale codes GAN encoder. The Visual Computer 2023, 40, 699 -715.

Zihao Guo, Mingwen Shao, Shunhang Li. Image-to-image translation using an offset-based multi-scale codes GAN encoder. The Visual Computer. 2023; 40 (2):699-715.

Zihao Guo; Mingwen Shao; Shunhang Li. 2023. "Image-to-image translation using an offset-based multi-scale codes GAN encoder." The Visual Computer 40, no. 2: 699-715.

Changzhong Wang; Yang Huang; Xiaodong Fan; Mingwen Shao. Homomorphism between ordered decision systems. Soft Computing 2018, 23, 365 -374.

Changzhong Wang, Yang Huang, Xiaodong Fan, Mingwen Shao. Homomorphism between ordered decision systems. Soft Computing. 2018; 23 (2):365-374.

Changzhong Wang; Yang Huang; Xiaodong Fan; Mingwen Shao. 2018. "Homomorphism between ordered decision systems." Soft Computing 23, no. 2: 365-374.

Chen Guo; Yaojin Lin; Meiyan Xu; Mingwen Shao; Junfeng Yao. Inverse transformation sampling-based attentive cutout for fine-grained visual recognition. The Visual Computer 2022, 39, 2597 -2608.

Chen Guo, Yaojin Lin, Meiyan Xu, Mingwen Shao, Junfeng Yao. Inverse transformation sampling-based attentive cutout for fine-grained visual recognition. The Visual Computer. 2022; 39 (7):2597-2608.

Chen Guo; Yaojin Lin; Meiyan Xu; Mingwen Shao; Junfeng Yao. 2022. "Inverse transformation sampling-based attentive cutout for fine-grained visual recognition." The Visual Computer 39, no. 7: 2597-2608.

Existing label assignment strategies have achieved promising performance for providing learning targets, typically rely on statistical information and location characteristics. However, classical label assignment strategies usually lack a comprehensive quality evaluation criterion. As a result, the quality of positive samples is not reliable, which weakens the performance of detectors. We propose a dynamic label assignment strategy to provide higher quality positive samples for detection models. Specifically, we propose a quality assessment criteria of candidate samples, which uses a joint representation guided by intersection over union (IoU). Consequently, the supervised information of both branches is included using only one metric. Beside, we propose a partitioning approach to eliminate local redundant sampling, allowing the selected positive sample points to focus more on the overall information of the target. Tests on the COCO dataset show that our work improves the baseline by 2.2% AP without additional modeling and supervisory information. In addition, extensive experiments on the MS COCO test-dev dataset using different backbones demonstrate that our best model outperforms most of the existing representative methods.

Zilu Peng; Mingwen Shao; Yuantao Sun; Zeting Liu; Cunhe Li. Instance-based dynamic label assignment for object detection. Journal of Electronic Imaging 2022, 31, 043009 .

Zilu Peng, Mingwen Shao, Yuantao Sun, Zeting Liu, Cunhe Li. Instance-based dynamic label assignment for object detection. Journal of Electronic Imaging. 2022; 31 (04):043009.

Zilu Peng; Mingwen Shao; Yuantao Sun; Zeting Liu; Cunhe Li. 2022. "Instance-based dynamic label assignment for object detection." Journal of Electronic Imaging 31, no. 04: 043009.

Changzhong Wang; Yunpeng Shi; Xiaodong Fan; Mingwen Shao. Attribute reduction based on k-nearest neighborhood rough sets. International Journal of Approximate Reasoning 2018, 106, 18 -31.

Changzhong Wang, Yunpeng Shi, Xiaodong Fan, Mingwen Shao. Attribute reduction based on k-nearest neighborhood rough sets. International Journal of Approximate Reasoning. 2018; 106 ():18-31.

Changzhong Wang; Yunpeng Shi; Xiaodong Fan; Mingwen Shao. 2018. "Attribute reduction based on k-nearest neighborhood rough sets." International Journal of Approximate Reasoning 106, no. : 18-31.

Qiwang Li; Mingwen Shao; Fukang Liu; Yuanjian Qiao; Zhiyong Hu. Contrastive local constraint for irregular image reconstruction and editability. The Visual Computer 2024, 1 -14.

Qiwang Li, Mingwen Shao, Fukang Liu, Yuanjian Qiao, Zhiyong Hu. Contrastive local constraint for irregular image reconstruction and editability. The Visual Computer. 2024; ():1-14.

Qiwang Li; Mingwen Shao; Fukang Liu; Yuanjian Qiao; Zhiyong Hu. 2024. "Contrastive local constraint for irregular image reconstruction and editability." The Visual Computer , no. : 1-14.

Yecong Wan; Mingwen Shao; Yuanshuo Cheng; Wangmeng Zuo. Image all-in-one adverse weather removal via dynamic model weights generation. Knowledge-Based Systems 2024, 302 .

Yecong Wan, Mingwen Shao, Yuanshuo Cheng, Wangmeng Zuo. Image all-in-one adverse weather removal via dynamic model weights generation. Knowledge-Based Systems. 2024; 302 ():.

Yecong Wan; Mingwen Shao; Yuanshuo Cheng; Wangmeng Zuo. 2024. "Image all-in-one adverse weather removal via dynamic model weights generation." Knowledge-Based Systems 302, no. : .

Changzhong Wang; Qiang He; Mingwen Shao; Yangyang Xu; Qinghua Hu. A unified information measure for general binary relations. Knowledge-Based Systems 2017, 135, 18 -28.

Changzhong Wang, Qiang He, Mingwen Shao, Yangyang Xu, Qinghua Hu. A unified information measure for general binary relations. Knowledge-Based Systems. 2017; 135 ():18-28.

Changzhong Wang; Qiang He; Mingwen Shao; Yangyang Xu; Qinghua Hu. 2017. "A unified information measure for general binary relations." Knowledge-Based Systems 135, no. : 18-28.

Mingwen Shao; Xinkai Zhuang; Lixu Zhang; Wangmeng Zuo. Pseudo initialization based Few-Shot Class Incremental Learning. Computer Vision and Image Understanding 2024, 247 .

Mingwen Shao, Xinkai Zhuang, Lixu Zhang, Wangmeng Zuo. Pseudo initialization based Few-Shot Class Incremental Learning. Computer Vision and Image Understanding. 2024; 247 ():.

Mingwen Shao; Xinkai Zhuang; Lixu Zhang; Wangmeng Zuo. 2024. "Pseudo initialization based Few-Shot Class Incremental Learning." Computer Vision and Image Understanding 247, no. : .

Because small targets have fewer pixels and carry fewer features, most target detection algorithms cannot effectively use the edge information and semantic information of small targets in the feature map, resulting in low detection accuracy, missed detections, and false detections from time to time. To solve the shortcoming of insufficient information features of small targets in the RetinaNet, this work introduces a parallel-assisted multi-scale feature enhancement module MFEM (Multi-scale Feature Enhancement Model), which uses dilated convolution with different expansion rates to avoid multiple down sampling. MFEM avoids information loss caused by multiple down sampling, and at the same time helps to assist shallow extraction of multi-scale context information. Additionally, this work adopts a backbone network improvement plan specifically designed for target detection tasks, which can effectively save small target information in high-level feature maps. The traditional top-down pyramid structure focuses on transferring high-level semantics from the top to the bottom, and the one-way information flow is not conducive to the detection of small targets. In this work, the auxiliary MFEM branch is combined with RetinaNet to construct a model with a bidirectional feature pyramid network, which can effectively integrate the strong semantic information of the high-level network and high-resolution information regarding the low level. The bidirectional feature pyramid network designed in this work is a symmetrical structure, including a top-down branch and a bottom-up branch, performs the transfer and fusion of strong semantic information and strong resolution information. To prove the effectiveness of the algorithm FE-RetinaNet (Feature Enhancement RetinaNet), this work conducts experiments on the MS COCO. Compared with the original RetinaNet, the improved RetinaNet has achieved a 1.8% improvement in the detection accuracy (mAP) on the MS COCO, and the COCO AP is 36.2%; FE-RetinaNet has a good detection effect on small targets, with APs increased by 3.2%.

Hong Liang; Junlong Yang; Mingwen Shao. FE-RetinaNet: Small Target Detection with Parallel Multi-Scale Feature Enhancement. Symmetry 2021, 13, 950 .

Hong Liang, Junlong Yang, Mingwen Shao. FE-RetinaNet: Small Target Detection with Parallel Multi-Scale Feature Enhancement. Symmetry. 2021; 13 (6):950.

Hong Liang; Junlong Yang; Mingwen Shao. 2021. "FE-RetinaNet: Small Target Detection with Parallel Multi-Scale Feature Enhancement." Symmetry 13, no. 6: 950.