Papers › TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label...

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training

20 Dec 2023arXiv:2312.12828archive 2025-07-28

Yuqi Lin, Minghao Chen, Kaipeng Zhang, Hengjia Li, Mingming Li, Zheng Yang, Dongqin Lv, Binbin Lin, Haifeng Liu, Deng Cai

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text descriptions supervised by contrastive loss, making it highly effective for single-label classification. However, it shows poor performance on multi-label datasets because the global feature tends to be dominated by the most prominent class and the contrastive nature of softmax operation aggravates it. In this study, we observe that the multi-label classification results heavily rely on discriminative local features but are overlooked by CLIP. As a result, we dissect the preservation of patch-wise spatial information in CLIP and proposed a local-to-global framework to obtain image tags. It comprises three steps: (1) patch-level classification to obtain coarse scores; (2) dual-masking attention refinement (DMAR) module to refine the coarse scores; (3) class-wise reidentification (CWR) module to remedy predictions from a global perspective. This framework is solely based on frozen CLIP and significantly enhances its multi-label classification performance on various benchmarks without dataset-specific training. Besides, to comprehensively assess the quality and practicality of generated tags, we extend their application to the downstream task, i.e., weakly supervised semantic segmentation (WSSS) with generated tags as image-level pseudo labels. Experiments demonstrate that this classify-then-segment paradigm dramatically outperforms other annotation-free segmentation methods and validates the effectiveness of generated tags. Our code is available at https://github.com/linyq2117/TagCLIP.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

linyq2117/tagclip officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationSemantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-trainingWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Object CLS-SEG mIoU 35.3 #5 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-27 CLS-SEG mIoU 31.0 #2 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL VOC CLS-SEG mIoU 68.7 #4 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CLIPSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections