Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2022
Abstract
Extracting class activation maps (CAM) is arguably the most standard step of generating pseudo masks for weakly supervised semantic segmentation (WSSS). Yet, we find that the crux of the unsatisfactory pseudo masks is the binary cross-entropy loss (BCE) widely used in CAM. Specifically, due to the sum-over-class pooling nature of BCE, each pixel in CAM may be responsive to multiple classes co-occurring in the same receptive field. To this end, we introduce an embarrassingly simple yet surprisingly effective method: Reactivating the converged CAM with BCE by using softmax crossentropy loss (SCE), dubbed ReCAM. Given an image, we use CAM to extract the feature pixels of each single class, and use them with the class label to learn another fully-connected layer (after the backbone) with SCE. Once converged, we extract ReCAM in the same way as in CAM.
Keywords
class activation maps, weakly supervised learning, semantic segmentation
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces
Research Areas
Data Science and Engineering
Publication
Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, June 18-24
First Page
969
Last Page
978
ISBN
9781665469463
Identifier
10.1109/CVPR52688.2022.00104
Publisher
IEEE
City or Country
New Orleans, Louisiana
Citation
CHEN, Zhaozheng; WANG, Tan; WU, Xiongwei; HUA, Xian-Sheng; ZHANG, Hanwang; and SUN, Qianru.
Class re-activation maps for weakly-supervised semantic segmentation. (2022). Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, June 18-24. 969-978.
Available at: https://ink.library.smu.edu.sg/sis_research/7511
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
http://doi.org/10.1109/CVPR52688.2022.00104
Included in
Databases and Information Systems Commons, Graphics and Human Computer Interfaces Commons