Papers › CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching

CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching

23 Mar 2023CVPR 2023 1arXiv:2303.13076archive 2025-07-28

Xiaoshi Wu, Feng Zhu, Rui Zhao, Hongsheng Li

Open-vocabulary detection (OVD) is an object detection task aiming at detecting objects from novel categories beyond the base categories on which the detector is trained. Recent OVD methods rely on large-scale visual-language pre-trained models, such as CLIP, for recognizing novel objects. We identify the two core obstacles that need to be tackled when incorporating these models into detector training: (1) the distribution mismatch that happens when applying a VL-model trained on whole images to region recognition tasks; (2) the difficulty of localizing objects of unseen classes. To overcome these obstacles, we propose CORA, a DETR-style framework that adapts CLIP for Open-vocabulary detection by Region prompting and Anchor pre-matching. Region prompting mitigates the whole-to-region distribution gap by prompting the region features of the CLIP-based region classifier. Anchor pre-matching helps learning generalizable object localization by a class-aware matching mechanism. We evaluate CORA on the COCO OVD benchmark, where we achieve 41.7 AP50 on novel classes, which outperforms the previous SOTA by 2.4 AP50 even without resorting to extra training data. When extra training data is available, we train CORA^+ on both ground-truth base-category annotations and additional pseudo bounding box labels computed by CORA. CORA^+ achieves 43.1 AP50 on the COCO OVD benchmark and 28.1 box APr on the LVIS OVD benchmark.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2303.13076")

Code

Syntology Ran 2 of 3 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 3 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tgxs002/cora 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

3 samples harvested; 2 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
1unverified

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tgxs002/CORA. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

gen_sineembed_for_position tgxs002/CORA/models/fast_detr.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 1455637eb5d8b21d · report
nested_tensor_from_tensor_list tgxs002/CORA/models/fast_detr.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 6c586ce97f1675d6 · report
FastDETR tgxs002/CORA/models/fast_detr.py official repository unverified Apache-2.0 (permissive) · 465f0a217286c663 · report

Tasks

Described Object DetectionObject DetectionObject LocalizationOpen Vocabulary Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Described Object Detection Description Detection Dataset CORA-R50 Intra-scenario ABS mAP 5.0 #8 of 8 Archive leaderboard report
Described Object Detection Description Detection Dataset CORA-R50 Intra-scenario FULL mAP 6.2 #8 of 8 Archive leaderboard report
Described Object Detection Description Detection Dataset CORA-R50 Intra-scenario PRES mAP 6.7 #8 of 8 Archive leaderboard report
Open Vocabulary Object Detection MSCOCO CORA+ AP 0.5 43.1 #8 of 32 Archive leaderboard report
Open Vocabulary Object Detection MSCOCO CORA AP 0.5 41.7 #11 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

BASECLIP

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