Papers › Dense Distinct Query for End-to-End Object Detection

Dense Distinct Query for End-to-End Object Detection

22 Mar 2023CVPR 2023 1arXiv:2303.12776archive 2025-07-28

Shilong Zhang, Xinjiang Wang, Jiaqi Wang, Jiangmiao Pang, Chengqi Lyu, Wenwei Zhang, Ping Luo, Kai Chen

One-to-one label assignment in object detection has successfully obviated the need for non-maximum suppression (NMS) as postprocessing and makes the pipeline end-to-end. However, it triggers a new dilemma as the widely used sparse queries cannot guarantee a high recall, while dense queries inevitably bring more similar queries and encounter optimization difficulties. As both sparse and dense queries are problematic, then what are the expected queries in end-to-end object detection? This paper shows that the solution should be Dense Distinct Queries (DDQ). Concretely, we first lay dense queries like traditional detectors and then select distinct ones for one-to-one assignments. DDQ blends the advantages of traditional and recent end-to-end detectors and significantly improves the performance of various detectors including FCN, R-CNN, and DETRs. Most impressively, DDQ-DETR achieves 52.1 AP on MS-COCO dataset within 12 epochs using a ResNet-50 backbone, outperforming all existing detectors in the same setting. DDQ also shares the benefit of end-to-end detectors in crowded scenes and achieves 93.8 AP on CrowdHuman. We hope DDQ can inspire researchers to consider the complementarity between traditional methods and end-to-end detectors. The source code can be found at \url{https://github.com/jshilong/DDQ}.

PaperPDFConference PDFCode

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

Code

jshilong/ddq officialmentioned in papermentioned on GitHubpytorch report
wokaikaixinxin/rqformer mentioned 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

ObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection CrowdHuman (full body) DDQ DETR (R50) AP 93.8 #4 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) DDQ DETR (R50) Recall 98.7 #4 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) DDQ DETR (R50) mMR 39.7 #4 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) DDQ R-CNN (R50) AP 93.5 #5 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) DDQ R-CNN (R50) Recall 98.6 #5 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) DDQ R-CNN (R50) mMR 40.4 #5 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) DDQ FCN (R50 One-Stage) AP 92.7 #7 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) DDQ FCN (R50 One-Stage) Recall 98.2 #7 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) DDQ FCN (R50 One-Stage) mMR 41.0 #7 of 19 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

ConvolutionFCNMax Pooling

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