Weakly supervised segmentation with maximum bipartite graph matching

• المؤلفون الرئيسيون: Liu, Weide, Zhang, Chi, Lin, Guosheng, Hung, Tzu-Yi, Miao, Chunyan
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: مقال Conference or Workshop Item
• اللغة: English
• منشور في: 2021
• الموضوعات: Engineering::Computer science and engineering; Computer Vision; Graph Matching
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/151821

In the weakly supervised segmentation task with only image-level labels, a common step in many existing algorithms is first to locate the image regions corresponding to each existing class with the Class Activation Maps (CAMs), and then generate the pseudo ground truth masks based on the CAMs to tra...