SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2444-2452
DOI: 10.1609/aaai.v40i4.37230 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xiuli Bi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
In recent years, Contrastive Language-Image Pretraining (CLIP) has been widely applied to Weakly Supervised Semantic Segmentation (WSSS) tasks due to its powerful cross-modal semantic understanding capabilities. This paper proposes a novel Semantic and Spatial Rectification (SSR) method to address the limitations of existing CLIP-based weakly supervised semantic segmentation approaches: over-activation in non-target foreground regions and background areas. Specifically, at the semantic level, the Cross-Modal Prototype Alignment (CMPA) establishes a contrastive learning mechanism to enforce feature space alignment across modalities, reducing inter-class overlap while enhancing semantic correlations, to rectify over-activation in non-target foreground regions effectively; at the spatial level, the Superpixel-Guided Correction (SGC) leverages superpixel-based spatial priors to precisely filter out interference from non-target regions during affinity propagation, significantly rectifying background over-activation. Extensive experiments on the PASCAL VOC and MS COCO datasets demonstrate that our method outperforms all single-stage approaches, as well as more complex multi-stage approaches, achieving mIoU scores of 79.5% and 50.6%, respectively.
Zitieren
APA
Bi, X., Xiao, D., Fan, J., & Xiao, B. (2026). SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2444-2452. https://doi.org/10.1609/aaai.v40i4.37230
Vancouver
Bi X, Xiao D, Fan J, Xiao B. SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2444-2452. doi:10.1609/aaai.v40i4.37230
BibTeX
@article{Bi2026,
author = {Bi, Xiuli and Xiao, Die and Fan, Junchao and Xiao, Bin},
title = {SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {2444--2452},
doi = {10.1609/aaai.v40i4.37230}
}
EUVIMED