Escaping the CAM Shadow: Uncertainty-Guided Reliable Learning for Weakly Supervised Semantic Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2734-2742
DOI: 10.1609/aaai.v40i4.37262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Luyao Chang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Weakly supervised semantic segmentation (WSSS) suffers from an inherent mismatch between coarse image-level annotations and dense pixel-level predictions. To bridge this gap, existing methods primarily focus on generating refined class activation maps (CAM) as pseudo-labels. However, we argue that this focus is insufficient as it overlooks a critical component: the segmentation decoder. The decoder is typically trained through superficial alignment of predictions with pseudo-labels in the logit space. Given the noisy nature of such labels, this naive supervision leads to error accumulation and limits performance. To address this, we propose an Uncertainty-Guided Reliable Learning (UGRL) framework that exerts dual control to reshape the learning process, achieving robust supervision that escapes the CAM shadow. The cornerstone of UGRL is a prototype-driven uncertainty modeling module that estimates the reliability of class-wise supervision. The modeled uncertainty enables two synergistic control mechanisms. First, it adaptively modulates classification and segmentation losses, encouraging the model to learn from more trustworthy signals. Second, it guides the structuring of the decoder’s feature space. Rather than relying solely on superficial alignment, UGRL enforces deeper representation alignment by applying contrastive learning on reliable pixels. This enables rich semantic transfer to fine-grained segmentation details. Extensive experiments on PASCAL VOC and MS COCO demonstrate that our method surpasses other state-of-the-art WSSS methods.
Zitieren
APA
Chang, L., Chen, L., Yang, C., & Zhou, C. (2026). Escaping the CAM Shadow: Uncertainty-Guided Reliable Learning for Weakly Supervised Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2734-2742. https://doi.org/10.1609/aaai.v40i4.37262
Vancouver
Chang L, Chen L, Yang C, Zhou C. Escaping the CAM Shadow: Uncertainty-Guided Reliable Learning for Weakly Supervised Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2734-2742. doi:10.1609/aaai.v40i4.37262
BibTeX
@article{Chang2026,
author = {Chang, Luyao and Chen, Leiting and Yang, Chen and Zhou, Chuan},
title = {Escaping the CAM Shadow: Uncertainty-Guided Reliable Learning for Weakly Supervised Semantic Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {2734--2742},
doi = {10.1609/aaai.v40i4.37262}
}
EUVIMED