Papers › DETRs with Collaborative Hybrid Assignments Training

DETRs with Collaborative Hybrid Assignments Training

22 Nov 2022ICCV 2023 1arXiv:2211.12860archive 2025-07-28

Zhuofan Zong, Guanglu Song, Yu Liu

In this paper, we provide the observation that too few queries assigned as positive samples in DETR with one-to-one set matching leads to sparse supervision on the encoder's output which considerably hurt the discriminative feature learning of the encoder and vice visa for attention learning in the decoder. To alleviate this, we present a novel collaborative hybrid assignments training scheme, namely 𝒞o-DETR, to learn more efficient and effective DETR-based detectors from versatile label assignment manners. This new training scheme can easily enhance the encoder's learning ability in end-to-end detectors by training the multiple parallel auxiliary heads supervised by one-to-many label assignments such as ATSS and Faster RCNN. In addition, we conduct extra customized positive queries by extracting the positive coordinates from these auxiliary heads to improve the training efficiency of positive samples in the decoder. In inference, these auxiliary heads are discarded and thus our method introduces no additional parameters and computational cost to the original detector while requiring no hand-crafted non-maximum suppression (NMS). We conduct extensive experiments to evaluate the effectiveness of the proposed approach on DETR variants, including DAB-DETR, Deformable-DETR, and DINO-Deformable-DETR. The state-of-the-art DINO-Deformable-DETR with Swin-L can be improved from 58.5% to 59.5% AP on COCO val. Surprisingly, incorporated with ViT-L backbone, we achieve 66.0% AP on COCO test-dev and 67.9% AP on LVIS val, outperforming previous methods by clear margins with much fewer model sizes. Codes are available at https://github.com/Sense-X/Co-DETR.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 5 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 5 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sense-x/co-detr mentioned in papermentioned on GitHubpytorchMITSyntology: not harvested report
anenbergb/Co-DETR-TensorRT mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
siyuanliii/masa mentioned on GitHubApache-2.0Syntology: not harvested report
MindCode-4/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
code-implementation1/Code1 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

5 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
1unverified

Licence: 0 of the 5 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 anenbergb/Co-DETR-TensorRT. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

anenbergb/Co-DETR-TensorRT community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
build_MLP codetr/transformer.py ran Apache-2.0 (permissive) · fb28f2ba259e8f13 · report fixture: signature input_dim:int/0/int, hidden_dim:int/0/int, output_dim:int/0/int, num_layers:int/0/int · returned Sequential · level recorded 2026-09-25
get_reference_points in 6 papers codetr/transformer.py ran Apache-2.0 (permissive) · 012e330e87684edc · report fixture: signature mlvl_feats:list/1/Tensor, valid_ratios:Tensor/3/float, device:device/0/? · returned Tensor · level recorded 2026-09-25
multi_scale_deformable_attention_pytorch codetr/ops.py ran Apache-2.0 (permissive) · 5502568acd4c6cdf · report fixture: signature value:Tensor/4/float, value_spatial_shapes:Tensor/2/int, sampling_locations:Tensor/6/float, attention_weights:Tensor/5/float · returned Tensor · level recorded 2026-09-25
swin_converter codetr/swin.py ran Apache-2.0 (permissive) · 85e307a3efdf4aa0 · report fixture: signature ckpt:dict/0/? · returned OrderedDict · level recorded 2026-09-25
make_encoder_output_proposals codetr/transformer.py unverified Apache-2.0 (permissive) · 2f3e30980c10ac1c · report

Tasks

DecoderInstance SegmentationObject Detectionset matching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival Co-DETR AP50 79.7 #1 of 93 Archive leaderboard report
Instance Segmentation COCO minival Co-DETR AP75 62.8 #1 of 93 Archive leaderboard report
Instance Segmentation COCO minival Co-DETR APL 74.6 #1 of 93 Archive leaderboard report
Instance Segmentation COCO minival Co-DETR APM 59.7 #1 of 93 Archive leaderboard report
Instance Segmentation COCO minival Co-DETR APS 38.9 #1 of 93 Archive leaderboard report
Instance Segmentation COCO minival Co-DETR mask AP 56.6 #1 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev Co-DETR AP50 80.2 #1 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Co-DETR AP75 63.4 #1 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Co-DETR APL 72.0 #1 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Co-DETR APM 60.1 #1 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Co-DETR APS 41.6 #1 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Co-DETR mask AP 57.1 #1 of 112 Archive leaderboard report
Instance Segmentation LVIS v1.0 val Co-DETR (single-scale) mask AP 60.7 #1 of 25 Archive leaderboard report
Object Detection COCO minival Co-DETR Params (M) 314 #2 of 220 Archive leaderboard report
Object Detection COCO minival Co-DETR box AP 65.9 #2 of 220 Archive leaderboard report
Object Detection COCO minival Co-DETR (Swin-L) Params (M) 218 #5 of 220 Archive leaderboard report
Object Detection COCO minival Co-DETR (Swin-L) box AP 64.7 #5 of 220 Archive leaderboard report
Object Detection COCO test-dev Co-DETR Params (M) 304 #1 of 225 Archive leaderboard report
Object Detection COCO test-dev Co-DETR box mAP 66.0 #1 of 225 Archive leaderboard report
Object Detection COCO test-dev Co-DETR (Swin-L) Params (M) 218 #6 of 225 Archive leaderboard report
Object Detection COCO test-dev Co-DETR (Swin-L) box mAP 64.8 #6 of 225 Archive leaderboard report
Object Detection LVIS v1.0 minival Co-DETR (single-scale) box AP 72.0 #1 of 6 Archive leaderboard report
Object Detection LVIS v1.0 val Co-DETR (single-scale) box AP 68.0 #1 of 15 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

1x1 ConvolutionATSSAbsolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDetrDropoutFCOSFPNFeedforward NetworkLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionNon Maximum SuppressionPosition-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