W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 7042-7050
DOI: 10.1609/aaai.v38i7.28531 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Fangyuan Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Current weakly-supervised semantic segmentation (WSSS) techniques concentrate on enhancing class activation maps (CAMs) with image-level annotations. Yet, the emphasis on producing these pseudo-labels often overshadows the pivotal role of training the segmentation model itself. This paper underscores the significant influence of noisy pseudo-labels on segmentation network performance, particularly in boundary region. To address above issues, we introduce a novel paradigm: Weak to Partial Supervision (W2P). At its core, W2P categorizes the pseudo-labels from WSSS into two unique supervisions: trustworthy clean labels and uncertain noisy labels. Next, our proposed partially-supervised framework adeptly employs these clean labels to rectify the noisy ones, thereby promoting the continuous enhancement of the segmentation model. To further optimize boundary segmentation, we incorporate a noise detection mechanism that specifically preserves boundary regions while eliminating noise. During the noise refinement phase, we adopt a boundary-conscious noise correction technique to extract comprehensive boundaries from noisy areas. Furthermore, we devise a boundary generation approach that assists in predicting intricate boundary zones. Evaluations on the PASCAL VOC 2012 and MS COCO 2014 datasets confirm our method's impressive segmentation capabilities across various pseudo-labels.
Zitieren
APA
Zhang, F., Pan, T., Yong, J., & Wang, B. (2024). W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7042-7050. https://doi.org/10.1609/aaai.v38i7.28531
Vancouver
Zhang F, Pan T, Yong J, Wang B. W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):7042-7050. doi:10.1609/aaai.v38i7.28531
BibTeX
@article{Zhang2024,
author = {Zhang, Fangyuan and Pan, Tianxiang and Yong, Jun-Hai and Wang, Bin},
title = {W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {7},
pages = {7042--7050},
doi = {10.1609/aaai.v38i7.28531}
}
EUVIMED