Papers › RegionCLIP: Region-based Language-Image Pretraining

RegionCLIP: Region-based Language-Image Pretraining

16 Dec 2021CVPR 2022 1arXiv:2112.09106archive 2025-07-28

Yiwu Zhong, Jianwei Yang, Pengchuan Zhang, Chunyuan Li, Noel Codella, Liunian Harold Li, Luowei Zhou, Xiyang Dai, Lu Yuan, Yin Li, Jianfeng Gao

Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to poor performance due to a domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans. To mitigate this issue, we propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visual representations, thus enabling fine-grained alignment between image regions and textual concepts. Our method leverages a CLIP model to match image regions with template captions and then pretrains our model to align these region-text pairs in the feature space. When transferring our pretrained model to the open-vocabulary object detection tasks, our method significantly outperforms the state of the art by 3.8 AP50 and 2.2 AP for novel categories on COCO and LVIS datasets, respectively. Moreoever, the learned region representations support zero-shot inference for object detection, showing promising results on both COCO and LVIS datasets. Our code is available at https://github.com/microsoft/RegionCLIP.

PaperPDFConference PDFCode

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

Code

microsoft/regionclip officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

Image ClassificationObjectObject DetectionOpen Vocabulary Object DetectionOpen-vocabulary object detectionReal-Time Object DetectionTransfer Learningimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Object Detection LVIS v1.0 Region-CLIP (RN50x4-C4) AP novel-LVIS base training 22.0 #19 of 28 Archive leaderboard report
Open Vocabulary Object Detection LVIS v1.0 Region-CLIP (RN50-C4) AP novel-LVIS base training 17.1 #26 of 28 Archive leaderboard report
Open Vocabulary Object Detection MSCOCO Region-CLIP (RN50x4-C4) AP 0.5 39.3 #14 of 32 Archive leaderboard report
Open Vocabulary Object Detection MSCOCO Region-CLIP (RN50-C4) AP 0.5 31.4 #23 of 32 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