Papers › OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World...

OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision

28 May 2024arXiv:2405.17913archive 2025-07-28

Junjie Wang, Bin Chen, Bin Kang, Yulin Li, YiChi Chen, Weizhi Xian, Huifeng Chang, Yong Xu

Open-vocabulary detection aims to detect objects from novel categories beyond the base categories on which the detector is trained. However, existing open-vocabulary detectors trained on base category data tend to assign higher confidence to trained categories and confuse novel categories with the background. To resolve this, we propose OV-DQUO, an \textbf{O}pen-\textbf{V}ocabulary DETR with \textbf{D}enoising text \textbf{Q}uery training and open-world \textbf{U}nknown \textbf{O}bjects supervision. Specifically, we introduce a wildcard matching method. This method enables the detector to learn from pairs of unknown objects recognized by the open-world detector and text embeddings with general semantics, mitigating the confidence bias between base and novel categories. Additionally, we propose a denoising text query training strategy. It synthesizes foreground and background query-box pairs from open-world unknown objects to train the detector through contrastive learning, enhancing its ability to distinguish novel objects from the background. We conducted extensive experiments on the challenging OV-COCO and OV-LVIS benchmarks, achieving new state-of-the-art results of 45.6 AP50 and 39.3 mAP on novel categories respectively, without the need for additional training data. Models and code are released at \url{https://github.com/xiaomoguhz/OV-DQUO}

PaperPDFCodeCode 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="2405.17913")

Code

Syntology Ran 9 of 11 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xiaomoguhz/ov-dquo 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

11 samples harvested; 9 ran; 1 honoured the contract we drafted; 2 have 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 · honoured contract
1ran · our draft was wrong
1ran · fixture could not drive it
6ran
2unverified

Licence: 0 of the 11 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 xiaomoguhz/ov-dquo. “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.

convert_to_xywh xiaomoguhz/ov-dquo/datasets/coco_eval.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · f31a58bf6457ced5 · report
dn_post_process xiaomoguhz/ov-dquo/models/ov_dquo/ov_dn_components.py official repository ran Apache-2.0 (permissive) · 0136c1e716ef3276 · report
evaluate xiaomoguhz/ov-dquo/datasets/coco_eval.py official repository ran · our draft was wrong Apache-2.0 (permissive) · fe0ddcc2d420c9a0 · report
gen_encoder_output_proposals xiaomoguhz/ov-dquo/models/ov_dquo/utils.py official repository ran Apache-2.0 (permissive) · e3b2768e6a9c1cb5 · report
gen_sineembed_for_position xiaomoguhz/ov-dquo/models/ov_dquo/utils.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 4c82654ae6131ecc · report
generate_deterministic_rand xiaomoguhz/ov-dquo/engine.py official repository ran fingerprinted Apache-2.0 (permissive) · dbde9f756c9f67d9 · report
label2onehot xiaomoguhz/ov-dquo/datasets/coco.py official repository ran Apache-2.0 (permissive) · fb05961e12a99588 · report
sigmoid_focal_loss xiaomoguhz/ov-dquo/models/ov_dquo/utils.py official repository ran Apache-2.0 (permissive) · f09e169e2656c2f7 · report
targets_preprocess xiaomoguhz/ov-dquo/models/ov_dquo/ov_dn_components.py official repository ran Apache-2.0 (permissive) · 413e6183a3918686 · report
ciou xiaomoguhz/ov-dquo/util/box_loss.py official repository unverified Apache-2.0 (permissive) · 4373b99bf6b5fd7d · report
diou xiaomoguhz/ov-dquo/util/box_loss.py official repository unverified Apache-2.0 (permissive) · 7818a5040676702a · report

Tasks

Contrastive LearningDenoisingObject DetectionOpen Vocabulary Object DetectionZero-Shot Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Object Detection LVIS v1.0 OV-DQUO(ViT-L/14) AP novel-LVIS base training 39.3 #3 of 28 Archive leaderboard report
Open Vocabulary Object Detection LVIS v1.0 OV-DQUO(ViT-B/16) AP novel-LVIS base training 29.7 #13 of 28 Archive leaderboard report
Open Vocabulary Object Detection MSCOCO OV-DQUO(RN50x4) AP 0.5 45.6 #5 of 32 Archive leaderboard report
Open Vocabulary Object Detection MSCOCO OV-DQUO(R50) AP 0.5 39.2 #15 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 EncodingsAdamAttentionBASEBPEConvolutionDense 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