Papers › ReCo: Retrieve and Co-segment for Zero-shot Transfer

ReCo: Retrieve and Co-segment for Zero-shot Transfer

14 Jun 2022arXiv:2206.07045archive 2025-07-28

Gyungin Shin, Weidi Xie, Samuel Albanie

Semantic segmentation has a broad range of applications, but its real-world impact has been significantly limited by the prohibitive annotation costs necessary to enable deployment. Segmentation methods that forgo supervision can side-step these costs, but exhibit the inconvenient requirement to provide labelled examples from the target distribution to assign concept names to predictions. An alternative line of work in language-image pre-training has recently demonstrated the potential to produce models that can both assign names across large vocabularies of concepts and enable zero-shot transfer for classification, but do not demonstrate commensurate segmentation abilities. In this work, we strive to achieve a synthesis of these two approaches that combines their strengths. We leverage the retrieval abilities of one such language-image pre-trained model, CLIP, to dynamically curate training sets from unlabelled images for arbitrary collections of concept names, and leverage the robust correspondences offered by modern image representations to co-segment entities among the resulting collections. The synthetic segment collections are then employed to construct a segmentation model (without requiring pixel labels) whose knowledge of concepts is inherited from the scalable pre-training process of CLIP. We demonstrate that our approach, termed Retrieve and Co-segment (ReCo) performs favourably to unsupervised segmentation approaches while inheriting the convenience of nameable predictions and zero-shot transfer. We also demonstrate ReCo's ability to generate specialist segmenters for extremely rare objects.

PaperPDFConference PDFCode

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

Code

NoelShin/reco officialmentioned in papermentioned on GitHubpytorch report
noelshin/namedmask mentioned 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

RetrievalSegmentationSemantic SegmentationUnsupervised Semantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-training

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Semantic Segmentation with Language-image Pre-training ADE20K ReCo Mean IoU (val) 11.2 #11 of 13 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Object ReCo mIoU 15.7 #12 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-171 ReCo mIoU 14.8 #11 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-27 ReCo+ mIoU 32.6 #1 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-27 ReCo+ pixel accuracy 54.1 #1 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-27 ReCo mIoU 26.3 #3 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-27 ReCo pixel accuracy 46.1 #3 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training Cityscapes val ReCo+ mIoU 24.2 #8 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training Cityscapes val ReCo+ pixel accuracy 83.7 #8 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training Cityscapes val ReCo mIoU 19.3 #10 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training Cityscapes val ReCo pixel accuracy 74.6 #10 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training KITTI-STEP ReCo+ mIoU 31.9 #1 of 3 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training KITTI-STEP ReCo+ pixel accuracy 75.3 #1 of 3 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training KITTI-STEP ReCo mIoU 29.8 #2 of 3 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training KITTI-STEP ReCo pixel accuracy 70.6 #2 of 3 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL Context-59 ReCo mIoU 22.3 #12 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PascalVOC-20 ReCo mIoU 57.7 #10 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

CLIP

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