SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation

2025-12-01 · Xiuli Bi, Die Xiao, Junchao Fan, Bin Xiao arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.01701

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Segmentation Contrastive Learning

Results from the Paper

Rank	Task	Dataset	Model	Metrics
#4	Semantic Segmentation	PASCAL VOC	Semantic	mIoU: 50.6

Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation

2022-11-22 · CVPR 2023 1 · Zesen Cheng, Pengchong Qiao, Kehan Li, Siheng Li 외

Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although tremendous efforts have been made to recall prec…

Optical Character Recognition (OCR)Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification

2025-09-18 · Tuo Xiang, Xuemiao Xu, Bangzhen Liu, Jinyi Li 외 arxiv

The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric m…

Few-Shot Class-Incremental Learning

FPR: False Positive Rectification for Weakly Supervised Semantic Segmentation

2023-01-01 · ICCV 2023 1 · Liyi Chen, Chenyang Lei, Ruihuang Li, Shuai Li 외

Many weakly supervised semantic segmentation (WSSS) methods employ the class activation map (CAM) to generate the initial segmentation results. However, CAM often fails to distinguish the foreground from its co-occur…

Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation

2024-06-17 · CVPR 2024 1 · Bingfeng Zhang, Siyue Yu, Yunchao Wei, Yao Zhao 외

Weakly supervised semantic segmentation has witnessed great achievements with image-level labels. Several recent approaches use the CLIP model to generate pseudo labels for training an individual segmentation model, whil…

Decoder Segmentation Semantic Segmentation Weakly supervised Semantic Segmentation+1

DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

2026-05-06 · Zhiwei Yang, Pengfei Song, Yucong Meng, Kexue Fu 외 arxiv

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has bee…

Semantic Segmentation