Papers › Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

22 May 2023arXiv:2305.13310archive 2025-07-28

Yang Liu, Muzhi Zhu, Hengtao Li, Hao Chen, Xinlong Wang, Chunhua Shen

Powered by large-scale pre-training, vision foundation models exhibit significant potential in open-world image understanding. However, unlike large language models that excel at directly tackling various language tasks, vision foundation models require a task-specific model structure followed by fine-tuning on specific tasks. In this work, we present Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks. Matcher can segment anything by using an in-context example without training. Additionally, we design three effective components within the Matcher framework to collaborate with these foundation models and unleash their full potential in diverse perception tasks. Matcher demonstrates impressive generalization performance across various segmentation tasks, all without training. For example, it achieves 52.7% mIoU on COCO-20ⁱ with one example, surpassing the state-of-the-art specialist model by 1.6%. In addition, Matcher achieves 33.0% mIoU on the proposed LVIS-92ⁱ for one-shot semantic segmentation, outperforming the state-of-the-art generalist model by 14.4%. Our visualization results further showcase the open-world generality and flexibility of Matcher when applied to images in the wild. Our code can be found at https://github.com/aim-uofa/Matcher.

PaperPDFCode

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

Code

aim-uofa/matcher officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

AllFew-Shot Semantic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) Matcher(DINOv2) Mean IoU 52.7 #5 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) Matcher(DINOv2) Mean IoU 60.7 #4 of 81 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