Weakly supervised segmentation with maximum bipartite graph matching
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...
Saved in:
Main Authors: | Liu, Weide, Zhang, Chi, Lin, Guosheng, Hung, Tzu-Yi, Miao, Chunyan |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article Conference or Workshop Item |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/151821 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
View-based 3D object retrieval by bipartite graph matching
by: Wen, Y., et al.
Published: (2013) -
View-based 3D Object Retrieval by Bipartite Graph Matching
by: WEN, Yue, et al.
Published: (2012) -
Adaptive dynamic bipartite graph matching : a reinforcement learning approach
by: Wang, Yansheng, et al.
Published: (2021) -
3D model retrieval using weighted bipartite graph matching
by: Gao, Y., et al.
Published: (2013) -
Cross-image region mining with region prototypical network for weakly supervised segmentation
by: Liu, Weide, et al.
Published: (2022)