MPMengyin Pang
Mengyin Pang
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mengyin Pang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Meijun Sun
Tianjin University
2 shared publications - Zheng Wang
Tianjin University
2 shared publications - Lina Wang
National Key Laboratory of Science and Technology on Aerospace Intelligence Control, Beijing Aerospace Automatic Control Institute, Beijing, China
1 shared publication Song Xu
Beijing Aerospace Automatic Control Institute
1 shared publicationZhenfei Liu
Beijing Aerospace Automatic Control Institute
1 shared publication
Latest Publications
- 11 March 2025
- Published by Springer Nature
- p. 211-221
Brain-Inspired Object Domain Adaptive Segmentation
- 11 March 2025
- Published by Springer Nature
- p. 211-221
Brain-Inspired Object Domain Adaptive Segmentation
- Open Access
- 28 December 2024
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 173
Curiosity-Driven Camouflaged Object Segmentation
Camouflaged object segmentation refers to the task of accurately extracting objects that are seamlessly integrated within their surrounding environment. Existing deep-learning methods frequently encounter challenges in accurately segmenting camouflaged objects, particularly in capturing their complete and intricate details. To this end, we propose a novel method based on the Curiosity-Driven network, which is motivated by the innate human tendency for curiosity when encountering ambiguous regions and the subsequent drive to explore and observe objects’ details. Specifically, the proposed fusion bridge module aims to exploit the model’s inherent curiosity to fuse these features extracted by the dual-branch feature encoder to capture the complete details of the object. Then, drawing inspiration from curiosity, the curiosity-refinement module is proposed to progressively refine the initial predictions by exploring unknown regions within the object’s surrounding environment. Notably, we develop a novel curiosity-calculation operation to discover and remove curiosity, leading to accurate segmentation results. Extensive quantitative and qualitative experiments demonstrate that the proposed model significantly outperforms the existing competitors on three challenging benchmark datasets. Compared with the recently proposed state-of-the-art method, our model achieves performance gains of on average for . Moreover, our model can be extended to the polyp and industrial defects segmentation tasks, validating its robustness and effectiveness.- 28 December 2024
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 173
Open AccessCuriosity-Driven Camouflaged Object Segmentation
Camouflaged object segmentation refers to the task of accurately extracting objects that are seamlessly integrated within their surrounding environment. Existing deep-learning methods frequently encounter challenges in accurately segmenting camouflaged objects, particularly in capturing their complete and intricate details. To this end, we propose a novel method based on the Curiosity-Driven network, which is motivated by the innate human tendency for curiosity when encountering ambiguous regions and the subsequent drive to explore and observe objects’ details. Specifically, the proposed fusion bridge module aims to exploit the model’s inherent curiosity to fuse these features extracted by the dual-branch feature encoder to capture the complete details of the object. Then, drawing inspiration from curiosity, the curiosity-refinement module is proposed to progressively refine the initial predictions by exploring unknown regions within the object’s surrounding environment. Notably, we develop a novel curiosity-calculation operation to discover and remove curiosity, leading to accurate segmentation results. Extensive quantitative and qualitative experiments demonstrate that the proposed model significantly outperforms the existing competitors on three challenging benchmark datasets. Compared with the recently proposed state-of-the-art method, our model achieves performance gains of on average for . Moreover, our model can be extended to the polyp and industrial defects segmentation tasks, validating its robustness and effectiveness.