Papers › TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification

TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification

21 Dec 2023arXiv:2312.14149archive 2025-07-28

Qinying Liu, Wei Wu, Kecheng Zheng, Zhan Tong, Jiawei Liu, Yu Liu, Wei Chen, Zilei Wang, Yujun Shen

The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data. Existing attempts usually face the problem of coarse alignment, e.g., the vision encoder struggles in localizing an attribute-specified object. In this work, we propose an embarrassingly simple approach to better align image and text features with no need of additional data formats other than image-text pairs. Concretely, given an image and its paired text, we manage to parse objects (e.g., cat) and attributes (e.g., black) from the description, which are highly likely to exist in the image. It is noteworthy that the parsing pipeline is fully automatic and thus enjoys good scalability. With these parsed semantics as supervision signals, we can complement the commonly used image-text contrastive loss with the multi-tag classification loss. Extensive experimental results on a broad suite of semantic segmentation datasets substantiate the average 5.2\% improvement of our framework over existing alternatives. Furthermore, the visualization results indicate that attribute supervision makes vision-language models accurately localize attribute-specified objects. Project page can be found at https://qinying-liu.github.io/Tag-Align.

PaperPDFCode

Code

Qinying-Liu/TagAlign officialmentioned on GitHubpytorch 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

AttributeOpen Vocabulary Semantic SegmentationSemantic SegmentationTAGUnsupervised Semantic Segmentation with Language-image Pre-training

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Semantic Segmentation PASCAL Context-59 TaAlign(trained with image-text pairs) mIoU 37.6 #19 of 24 Archive leaderboard report
Open Vocabulary Semantic Segmentation PascalVOC-20 TagAlign(trained with image-text pairs) mIoU 87.9 #14 of 20 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training ADE20K TagAlign Mean IoU (val) 17.3 #6 of 13 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Object TagAlign mIoU 33.3 #6 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-171 TagAlign mIoU 25.3 #5 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training Cityscapes val TagAlign mIoU 27.5 #6 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL Context-59 TagAlign mIoU 37.6 #5 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL VOC TagAlign mIoU 53.9 #8 of 10 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PascalVOC-20 TagAlign mIoU 87.9 #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.

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