Papers › Open-Vocabulary DETR with Conditional Matching

Open-Vocabulary DETR with Conditional Matching

22 Mar 2022arXiv:2203.11876archive 2025-07-28

Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, Chen Change Loy

Open-vocabulary object detection, which is concerned with the problem of detecting novel objects guided by natural language, has gained increasing attention from the community. Ideally, we would like to extend an open-vocabulary detector such that it can produce bounding box predictions based on user inputs in form of either natural language or exemplar image. This offers great flexibility and user experience for human-computer interaction. To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image. The biggest challenge of turning DETR into an open-vocabulary detector is that it is impossible to calculate the classification cost matrix of novel classes without access to their labeled images. To overcome this challenge, we formulate the learning objective as a binary matching one between input queries (class name or exemplar image) and the corresponding objects, which learns useful correspondence to generalize to unseen queries during testing. For training, we choose to condition the Transformer decoder on the input embeddings obtained from a pre-trained vision-language model like CLIP, in order to enable matching for both text and image queries. With extensive experiments on LVIS and COCO datasets, we demonstrate that our OV-DETR -- the first end-to-end Transformer-based open-vocabulary detector -- achieves non-trivial improvements over current state of the arts.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2203.11876")

Code

Syntology Ran 6 of 8 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 3 ran; community (archive-listed): 4 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yuhangzang/ov-detr officialmentioned in papermentioned on GitHubpytorch report
hchoi256/i-halla-v1.0 mentioned on GitHubMIT report
kaist-cvml-lab/part-clipseg mentioned on GitHubpytorchMIT report
kaist-cvml/part-clipseg mentioned on GitHubjaxMIT 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

8 samples harvested; 6 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
5ran
2unverified

Licence: 4 of the 8 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

DeformableDETR yuhangzang/OV-DETR/ovdetr/models/model.py official repository ran no licence file found · pointer only · 0415bb0bee56bc59 · report
NestedTensor yuhangzang/OV-DETR/ovdetr/models/model.py official repository ran no licence file found · pointer only · a59cf95e6b922e44 · report
nested_tensor_from_tensor_list yuhangzang/OV-DETR/ovdetr/models/model.py official repository ran · our draft was wrong no licence file found · pointer only · 57b6cc60d20c5e85 · report
OVDETR yuhangzang/OV-DETR/ovdetr/models/model.py official repository unverified no licence file found · pointer only · e82eea2c13d31778 · report
load_image hchoi256/i-halla-v1.0/utils.py community (archive-listed) ran fingerprinted MIT (permissive) · 2bdfadf4cfb18cd8 · report
parse_questions hchoi256/i-halla-v1.0/agents/CoIAgent.py community (archive-listed) ran fingerprinted MIT (permissive) · 69eda7e624ba1809 · report
parse_questions hchoi256/i-halla-v1.0/agents/QAAgent.py community (archive-listed) ran fingerprinted MIT (permissive) · 75d5bef2a1de5b6b · report
load_text hchoi256/i-halla-v1.0/utils.py community (archive-listed) unverified MIT (permissive) · 82658872a11788ab · report

Tasks

Language ModellingObject DetectionOpen Vocabulary Object DetectionOpen-vocabulary object detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Object Detection MSCOCO OV-DERT AP 0.5 29.4 #26 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

Absolute Position EncodingsAdamAttentionBPECLIPConvolutionDense ConnectionsDetrDropoutFeedforward NetworkLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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