SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 7525-7533
DOI: 10.1609/aaai.v38i7.28584 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xinqiao Zhao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 55-mal zitiert (Crossref).
Abstract (Originalsprache)
Image-level weakly supervised semantic segmentation has received increasing attention due to its low annotation cost. Existing methods mainly rely on Class Activation Mapping (CAM) to obtain pseudo-labels for training semantic segmentation models. In this work, we are the first to demonstrate that long-tailed distribution in training data can cause the CAM calculated through classifier weights over-activated for head classes and under-activated for tail classes due to the shared features among head- and tail- classes. This degrades pseudo-label quality and further influences final semantic segmentation performance. To address this issue, we propose a Shared Feature Calibration (SFC) method for CAM generation. Specifically, we leverage the class prototypes which carry positive shared features and propose a Multi-Scaled Distribution-Weighted (MSDW) consistency loss for narrowing the gap between the CAMs generated through classifier weights and class prototypes during training. The MSDW loss counterbalances over-activation and under-activation by calibrating the shared features in head-/tail-class classifier weights. Experimental results show that our SFC significantly improves CAM boundaries and achieves new state-of-the-art performances. The project is available at https://github.com/Barrett-python/SFC.
Zitieren
APA
Zhao, X., Tang, F., Wang, X., & Xiao, J. (2024). SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7525-7533. https://doi.org/10.1609/aaai.v38i7.28584
Vancouver
Zhao X, Tang F, Wang X, Xiao J. SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):7525-7533. doi:10.1609/aaai.v38i7.28584
BibTeX
@article{Zhao2024,
author = {Zhao, Xinqiao and Tang, Feilong and Wang, Xiaoyang and Xiao, Jimin},
title = {SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {7},
pages = {7525--7533},
doi = {10.1609/aaai.v38i7.28584}
}
EUVIMED