Papers › DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

28 Jan 2022ICLR 2022 4arXiv:2201.12329archive 2025-07-28

Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, Lei Zhang

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in Transformer decoders and dynamically updates them layer-by-layer. Using box coordinates not only helps using explicit positional priors to improve the query-to-feature similarity and eliminate the slow training convergence issue in DETR, but also allows us to modulate the positional attention map using the box width and height information. Such a design makes it clear that queries in DETR can be implemented as performing soft ROI pooling layer-by-layer in a cascade manner. As a result, it leads to the best performance on MS-COCO benchmark among the DETR-like detection models under the same setting, e.g., AP 45.7% using ResNet50-DC5 as backbone trained in 50 epochs. We also conducted extensive experiments to confirm our analysis and verify the effectiveness of our methods. Code is available at https://github.com/SlongLiu/DAB-DETR.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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

No sample from the archive's official repository (slongliu/dab-detr) is linked to this paper; the 11 samples below come from 3 community repositories. Syntology harvested code from slongliu/dab-detr for another paper.

slongliu/dab-detr: Syntology's graph links these samples to DN-DETR: Accelerate DETR Training by Introducing Query DeNoising (arXiv:2203.01305; that paper's own run record: 17 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples harvested from 3 repositories linked to this paper: 6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 3 repositories, 6 ran (4 with no instrument failure; 2 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

slongliu/dab-detr officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DN-DETR: Accelerate DETR Training by Introducing Query DeNoising (arXiv:2203.01305; that paper's own run record: 17 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
IDEA-Research/detrex mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Conditional DETR for Fast Training Convergence (arXiv:2108.06152; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified), DN-DETR: Accelerate DETR Training by Introducing Query DeNoising (arXiv:2203.01305; that paper's own run record: 17 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified), DETRs with Hybrid Matching (arXiv:2207.13080; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 2 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
Tajamul21/Detection-Classification-and-Semantic_Segmentation-of-apples mentioned on GitHubpytorchSyntology: not harvested report
helq2612/biadt mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 5 ran (1 instrument-failed) · 3 unverified report
horrible-dong/teamdetr mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection (arXiv:2203.03605; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
idea-research/dab-detr mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
idea-research/dn-detr mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
alibaba/EasyCV pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End-to-End Object Detection with Transformers (arXiv:2005.12872; that paper's own run record: 70 ran (of which 45 constructed an object rather than computing a result; 62 with no instrument failure: 2 honoured, 1 violated, 59 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified), 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), Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified) and 1 more (every one in this page's JSON twin); 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

11 samples harvested: 6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 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.

2ran · our draft was wrong
4ran
5unverified

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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

helq2612/biadt community (archive-listed) 8 samples, 5 ran (1 instrument-failed) · 3 unverified
GradientReversal models/dn_dab_deformable_detr/dab_deformable_detr.py ran fingerprinted Apache-2.0 (permissive) · 764f03e6f6c10909 · report fixture: returned GradientReversal · level recorded 2026-09-22
GradientReversalFunction models/dn_dab_deformable_detr/dab_deformable_detr.py ran Apache-2.0 (permissive) · 6e1a6cc4327acf17 · report fixture: returned GradientReversalFunction · level recorded 2026-09-22
Mutual_loss models/dn_dab_deformable_detr/dab_deformable_detr.py ran Apache-2.0 (permissive) · 79c4cf758452c514 · report fixture: signature xy:Tensor/3/float, zd:Tensor/3/float · returned Tensor · level recorded 2026-09-24
NestedTensor in 24 papers models/dn_dab_deformable_detr/dab_deformable_detr.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d336c6095b11629a · report fixture: returned NestedTensor · level recorded 2026-09-22
nested_tensor_from_tensor_list in 60 papers models/dn_dab_deformable_detr/dab_deformable_detr.py ran · our draft was wrong Apache-2.0 (permissive) · 6442da4f34dd152c · report fixture: signature tensor_list:list/1/Tensor · returned NestedTensor · level recorded 2026-09-22
DABDeformableDETR models/dn_dab_deformable_detr/dab_deformable_detr.py unverified Apache-2.0 (permissive) · fe79de37d598acb3 · report
_onnx_nested_tensor_from_tensor_list in 9 papers models/dn_dab_deformable_detr/dab_deformable_detr.py unverified Apache-2.0 (permissive) · 50ec3e702e11eebb · report
prepare_for_dn in 5 papers models/dn_dab_deformable_detr/dab_deformable_detr.py unverified Apache-2.0 (permissive) · af4a2db04af02c0a · report
idea-research/dab-detr community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/DAB_DETR/DABDETR.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5c0711aada67957e · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded, date not recorded
idea-research/dn-detr community (archive-listed) 2 samples, 0 ran · 2 unverified
DABDETR models/DN_DAB_DETR/DABDETR.py unverified Apache-2.0 (permissive) · 530114cee9263694 · report
prepare_for_dn in 5 papers models/DN_DAB_DETR/DABDETR.py unverified Apache-2.0 (permissive) · daa15d8205b6349a · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for DAB-DETR (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for DAB-DETR (graph method: DAB-DETR). 13 bricks; individually on a fixture: 10 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. DABDeformableDETR entry · level 0 · unverified · fe79de37d598acb3
  2. GradientReversal helper · level 1 · ran · 764f03e6f6c10909
  3. MLP helper · level 1 · ran · d71ab24dd4408288
  4. Mutual_loss loss · level 1 · ran · 79c4cf758452c514
  5. NestedTensor helper · level 1 · ran · d336c6095b11629a
  6. _get_clones helper · level 1 · ran · our draft was wrong · e63e66b61302a7a2
  7. dn_post_process helper · level 1 · ran; the contract check could not run · 9db6a2fdc3039d38
  8. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94
  9. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 6442da4f34dd152c
  10. prepare_for_dn helper · level 0 · unverified · af4a2db04af02c0a
  11. GradientReversalFunction helper · level 1 · ran · 6e1a6cc4327acf17
  12. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  13. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 50ec3e702e11eebb

harvested Assembly for DAB-DETR (graph method: DAB-DETR). 9 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. DABDETR entry · level 0 · unverified · 530114cee9263694
  2. MLP helper · level 1 · ran · d71ab24dd4408288
  3. NestedTensor helper · level 1 · ran · 5fcd889ee3ae8609
  4. dn_post_process helper · level 1 · ran; the contract check could not run · 9db6a2fdc3039d38
  5. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94
  6. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 966e78e3ec193e43
  7. prepare_for_dn helper · level 0 · unverified · daa15d8205b6349a
  8. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  9. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 49d50b270cc3e546

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2201.12329") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

2D Object DetectionObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival DAB-DETR-DC5-R101 AP50 67 #102 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-DC5-R101 AP75 50.2 #102 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-DC5-R101 APL 64.1 #102 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-DC5-R101 APM 50.5 #102 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-DC5-R101 APS 28.1 #102 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-DC5-R101 Params (M) 63 #102 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-DC5-R101 box AP 46.6 #102 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-R101 AP50 64.7 #135 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-R101 AP75 47.2 #135 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-R101 APL 62.9 #135 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-R101 APM 48.2 #135 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-R101 APS 24.1 #135 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-R101 Params (M) 63 #135 of 220 Archive leaderboard report
Object Detection COCO minival DAB-DETR-R101 box AP 44.1 #135 of 220 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 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