Papers › DETRs with Hybrid Matching

DETRs with Hybrid Matching

26 Jul 2022CVPR 2023 1arXiv:2207.13080archive 2025-07-28

Ding Jia, Yuhui Yuan, Haodi He, Xiaopei Wu, Haojun Yu, WeiHong Lin, Lei Sun, Chao Zhang, Han Hu

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-end signature is important for the versatility of DETR, and it has been generalized to broader vision tasks. However, we note that there are few queries assigned as positive samples and the one-to-one set matching significantly reduces the training efficacy of positive samples. We propose a simple yet effective method based on a hybrid matching scheme that combines the original one-to-one matching branch with an auxiliary one-to-many matching branch during training. Our hybrid strategy has been shown to significantly improve accuracy. In inference, only the original one-to-one match branch is used, thus maintaining the end-to-end merit and the same inference efficiency of DETR. The method is named H-DETR, and it shows that a wide range of representative DETR methods can be consistently improved across a wide range of visual tasks, including DeformableDETR, PETRv2, PETR, and TransTrack, among others. The code is available at: https://github.com/HDETR

PaperPDFConference PDFCodeCode 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="2207.13080")

Code

Syntology Ran 15 of 18 code samples harvested from 4 repositories linked to this paper; 3 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · violated contract; 5 ran · our draft was wrong; 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 17 samples from 3 repositories, 14 ran; community (archive-listed): 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

HDETR/H-Deformable-DETR officialmentioned on GitHubpytorchMIT report
HDETR/H-Deformable-DETR-mmdet officialmentioned on GitHubpytorchApache-2.0 report
HDETR/H-Detic-LVIS officialmentioned on GitHubpytorchApache-2.0 report
HDETR/H-PETR-3D officialmentioned on GitHubpytorch report
HDETR/H-PETR-Pose officialmentioned on GitHubpytorchMIT 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

18 samples harvested; 15 ran; 2 honoured the contract we drafted; 3 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.

2ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
2ran · fixture could not drive it
4ran
3unverified

Licence: 1 of the 18 samples is 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 4 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.

window_partition HDETR/H-Deformable-DETR/models/swin_transformer.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report
convert_to_xywh HDETR/H-Deformable-DETR/datasets/coco_eval.py official repository ran · honoured contract fingerprinted MIT (permissive) · f31a58bf6457ced5 · report
dice_loss HDETR/H-Deformable-DETR/models/segmentation.py official repository ran · violated contract fingerprinted MIT (permissive) · ac8fe530cdad4d8c · report
evaluate HDETR/H-Deformable-DETR/datasets/coco_eval.py official repository ran · our draft was wrong MIT (permissive) · fe0ddcc2d420c9a0 · report
get_clip_embeddings HDETR/H-Detic-LVIS/detic/predictor.py official repository ran Apache-2.0 (permissive) · 1f211df98dc51cee · report
get_fed_loss_inds HDETR/H-Detic-LVIS/detic/modeling/utils.py official repository ran Apache-2.0 (permissive) · bb583e07209fe58b · report
load_class_freq HDETR/H-Detic-LVIS/detic/modeling/utils.py official repository ran Apache-2.0 (permissive) · 1f6e4c3da7b82979 · report
match_name_keywords HDETR/H-Detic-LVIS/detic/custom_solver.py official repository ran · violated contract Apache-2.0 (permissive) · c15434906f804d7f · report
pos2posemb3d HDETR/H-PETR-3D/projects/mmdet3d_plugin/models/dense_heads/hybrid_petrv2_head.py official repository ran · our draft was wrong fingerprinted licence not identified · pointer only · 718ca707584a0928 · report
sigmoid_focal_loss HDETR/H-Deformable-DETR/models/segmentation.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5c0711aada67957e · report
train_hybrid HDETR/H-Deformable-DETR/engine.py official repository ran MIT (permissive) · 8cc99e95f95cb562 · report
window_partition HDETR/H-Detic-LVIS/detic/modeling/backbone/swintransformer.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · f9fd6241d935f07b · report
window_reverse HDETR/H-Deformable-DETR/models/swin_transformer.py official repository ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report
window_reverse HDETR/H-Detic-LVIS/detic/modeling/backbone/swintransformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · fb32094c6dbece71 · report
compute_average_precision HDETR/H-Detic-LVIS/detic/evaluation/oideval.py official repository unverified Apache-2.0 (permissive) · 2e0a799ccbd489e7 · report
create_timm_resnet HDETR/H-Detic-LVIS/detic/modeling/backbone/timm.py official repository unverified Apache-2.0 (permissive) · 3634f2208a0255d7 · report
measure_average_inference_time HDETR/H-Deformable-DETR/benchmark.py official repository unverified MIT (permissive) · 3e5d34f155e97585 · report
get_vit_lr_decay_rate IDEA-Research/detrex/detrex/modeling/backbone/eva.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · 08bf7ecdb2fffe84 · report

Tasks

Object DetectionPose EstimationSemantic Segmentationset matching

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEConvolutionDense 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