Papers › DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

2 Mar 2022CVPR 2022 1arXiv:2203.01305archive 2025-07-28

Feng Li, Hao Zhang, Shilong Liu, Jian Guo, Lionel M. Ni, Lei Zhang

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results from the instability of bipartite graph matching which causes inconsistent optimization goals in early training stages. To address this issue, except for the Hungarian loss, our method additionally feeds ground-truth bounding boxes with noises into Transformer decoder and trains the model to reconstruct the original boxes, which effectively reduces the bipartite graph matching difficulty and leads to a faster convergence. Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement. As a result, our DN-DETR results in a remarkable improvement (+1.9AP) under the same setting and achieves the best result (AP 43.4 and 48.6 with 12 and 50 epochs of training respectively) among DETR-like methods with ResNet-50 backbone. Compared with the baseline under the same setting, DN-DETR achieves comparable performance with 50% training epochs. Code is available at https://github.com/FengLi-ust/DN-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

Syntology 22 code samples harvested from 6 repositories linked to this paper: 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. Where Syntology's instrument failed: 4 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 2 repositories, 10 ran (2 with no instrument failure; 8 where Syntology's instrument failed); community (archive-listed): 10 samples from 4 repositories, 7 ran (4 with no instrument failure; 3 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 8 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. 3 of the 17 samples that ran have no recorded date.

17 repositories listed; official and paper-mentioned ones first.

IDEA-Research/detrex officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
fengli-ust/dn-detr officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 6 ran (5 instrument-failed) · 2 unverified report
idea-research/dn-detr officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR (arXiv:2201.12329; that paper's own run record: 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); nothing checks that they implement this paper's method. report
IDEA-opensource/DAB-DETR mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
IDEA-opensource/DN-DETR mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation (arXiv:2206.02777; that paper's own run record: 11 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; 9 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
IDEACVR/DINO mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation (arXiv:2206.02777; that paper's own run record: 11 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; 9 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
IDEACVR/MaskDINO 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
Tajamul21/Detection-Classification-and-Semantic_Segmentation-of-apples mentioned on GitHubpytorchSyntology: not harvested report
helq2612/biadt mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR (arXiv:2201.12329; that paper's own run record: 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) and CVF open access id He_Bidirectional_Alignment_for_Domain_Adaptive_Detection_with_Transformers_ICCV_2023_paper (that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR (arXiv:2201.12329; that paper's own run record: 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); nothing checks that they implement this paper's method. report
idea-research/dino 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/maskdino mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 6 ran (3 instrument-failed) · 1 unverified report
slongliu/dab-detr mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
2023-MindSpore-4/Code3 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code8 mindsporeSyntology: not harvested report
alibaba/EasyCV pytorchSyntology: 1 sample, 0 ran · 1 unverified 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

22 samples harvested: 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. “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.

1ran · violated contract
4ran · our draft was wrong
7ran; the contract check could not run
5ran
5unverified

Licence: 9 of the 22 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 6 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.

IDEA-Research/detrex official repository 4 samples, 4 ran (3 instrument-failed) · 0 unverified
GenerateDNQueries detrex/layers/denoising.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a33aa40d1ec31a21 · report fixture: returned GenerateDNQueries · level recorded 2026-09-22
apply_box_noise detrex/layers/denoising.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · c8ea5508b3ca2db0 · report fixture: signature boxes:Tensor/2/float, box_noise_scale:float/0/float · returned Tensor · level recorded 2026-09-22
apply_label_noise detrex/layers/denoising.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 95bd488170c50d24 · report fixture: signature labels:Tensor/1/int, label_noise_prob:float/0/float, num_classes:int/0/int · returned Tensor · level recorded 2026-09-22
inverse_sigmoid in 80 papers
census: 9 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
detrex/layers/denoising.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 49611009ffc9cf17 · report fixture: signature x:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
fengli-ust/dn-detr official repository 8 samples, 6 ran (5 instrument-failed) · 2 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/DN_DAB_DETR/swin_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 144d10b49baeb8a6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/DN_DAB_DETR/segmentation.py ran · violated contract fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · ac8fe530cdad4d8c · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int · returned Tensor · level recorded 2026-09-22
dn_post_process in 15 papers models/DN_DAB_DETR/dn_components.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic Apache-2.0 recorded; this copy not marked cleared · pointer only · 9db6a2fdc3039d38 · report fixture: signature outputs_class:Tensor/4/float, outputs_coord:Tensor/4/float, mask_dict:dict/0/? · returned tuple · level recorded 2026-09-22
gen_sineembed_for_position in 29 papers models/DN_DAB_DETR/transformer.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 1455637eb5d8b21d · report fixture: signature pos_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-22
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/DN_DAB_DETR/DABDETR.py ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 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
window_reverse in 296 papers models/DN_DAB_DETR/swin_transformer.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · 61bf152e6a42a184 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded, date not recorded
build_swin_transformer models/DN_DAB_DETR/swin_transformer.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · ddbe621fd9f33a35 · report
multi_head_attention_forward in 73 papers models/DN_DAB_DETR/attention.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · a82091666b9db8cf · report
IDEA-opensource/DAB-DETR community (archive-listed) 1 sample, 0 ran · 1 unverified
DABDETR models/DAB_DETR/DABDETR.py unverified Apache-2.0 (permissive) · 2f7664c2aea20776 · report
idea-research/maskdino community (archive-listed) 7 samples, 6 ran (3 instrument-failed) · 1 unverified
MLP in 375 papers maskdino/modeling/transformer_decoder/dino_decoder.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1a575c1c202174f0 · report fixture: returned MLP · level recorded 2026-09-22
MSDeformAttn in 13 papers maskdino/modeling/transformer_decoder/dino_decoder.py ran Apache-2.0 (permissive) · 107172bd7583403e · report fixture: signature query:Tensor/3/float, reference_points:Tensor/4/float, input_flatten:Tensor/3/float, input_spatial_shapes:Tensor/2/int, input_level_start_index:Tensor/1/int, input_padding_mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24
MSDeformAttnFunction maskdino/modeling/transformer_decoder/dino_decoder.py ran Apache-2.0 (permissive) · 7205a619c51dd0ee · report fixture: returned MSDeformAttnFunction · level recorded 2026-09-22
_get_clones in 28 papers maskdino/modeling/transformer_decoder/dino_decoder.py ran · our draft was wrong Apache-2.0 (permissive) · 82ab53eb37ba2bf3 · report fixture: signature module:callable/0/?, N:int/0/int, layer_share:bool/0/bool · returned ModuleList · level recorded 2026-09-22
gen_sineembed_for_position in 29 papers maskdino/modeling/transformer_decoder/dino_decoder.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 4c82654ae6131ecc · report fixture: signature pos_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-22
ms_deform_attn_core_pytorch in 7 papers maskdino/modeling/transformer_decoder/dino_decoder.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · c53ec291fabfc643 · report fixture: signature value:Tensor/4/float, value_spatial_shapes:list/1/tuple, sampling_locations:Tensor/6/float, attention_weights:Tensor/5/float · returned Tensor · level recorded 2026-09-22
TransformerDecoder in 49 papers maskdino/modeling/transformer_decoder/dino_decoder.py unverified Apache-2.0 (permissive) · 947c7bd4504c7501 · report
slongliu/dab-detr community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
gen_sineembed_for_position in 29 papers models/DAB_DETR/transformer.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 376e5a5c1b978006 · report fixture: signature pos_tensor:Tensor/3/float, d_model:int/0/int · returned Tensor · level recorded 2026-09-24
alibaba/EasyCV community (archive-listed) 1 sample, 0 ran · 1 unverified
prepare_for_dn in 5 papers easycv/models/detection/detectors/dab_detr/dn_components.py unverified Apache-2.0 (permissive) · fd0493bda2a2352e · 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.

7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

one of 7 siblings

  1. GenerateDNQueries entry · level 1 · ran · a33aa40d1ec31a21
  2. apply_box_noise helper · level 1 · ran; the contract check could not run (RAISES) · c8ea5508b3ca2db0
  3. apply_label_noise helper · level 1 · ran; the contract check could not run (RAISES) · 95bd488170c50d24
  4. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 49611009ffc9cf17

harvested Assembly for DN-DETR (graph method: DN-DETR). 9 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. TransformerDecoder entry · level 0 · unverified · 947c7bd4504c7501
  2. MLP helper · level 1 · ran · 1a575c1c202174f0
  3. MSDeformAttn helper · level 1 · ran · 107172bd7583403e
  4. _get_clones helper · level 1 · ran · our draft was wrong · 82ab53eb37ba2bf3
  5. gen_sineembed_for_position helper · level 1 · ran; the contract check could not run (RAISES) · 4c82654ae6131ecc
  6. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 83c03ceb1307c6c4
  7. MSDeformAttnFunction helper · level 1 · ran · 7205a619c51dd0ee
  8. _is_power_of_2 helper · level 1 · ran · violated contract · 2b45e8897cb1e2ea
  9. ms_deform_attn_core_pytorch helper · level 1 · ran; the contract check could not run (RAISES) · c53ec291fabfc643

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

one of 7 siblings

  1. prepare_for_dn entry · level 0 · unverified · fd0493bda2a2352e
  2. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94

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

one of 7 siblings

  1. prepare_for_cdn entry · level 1 · ran; the contract check could not run · e2cd5184b63b954d
  2. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94

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

one of 7 siblings

  1. prepare_for_dn entry · level 0 · unverified · daa15d8205b6349a
  2. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94

harvested Assembly for DN-DETR (graph method: DN-DETR). 7 bricks; individually on a fixture: 5 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; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. DABDETR entry · level 0 · unverified · 2f7664c2aea20776
  2. MLP helper · level 1 · ran · d71ab24dd4408288
  3. NestedTensor helper · level 1 · ran · 5fcd889ee3ae8609
  4. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94
  5. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 966e78e3ec193e43
  6. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  7. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 49d50b270cc3e546

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

one of 7 siblings

  1. prepare_for_dn entry · level 0 · unverified · af4a2db04af02c0a
  2. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94

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="2203.01305") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival DN-Deformable-DETR-R50++ AP50 67.6 #85 of 220 Archive leaderboard report
Object Detection COCO minival DN-Deformable-DETR-R50++ AP75 53.8 #85 of 220 Archive leaderboard report
Object Detection COCO minival DN-Deformable-DETR-R50++ APL 65.4 #85 of 220 Archive leaderboard report
Object Detection COCO minival DN-Deformable-DETR-R50++ APM 52.6 #85 of 220 Archive leaderboard report
Object Detection COCO minival DN-Deformable-DETR-R50++ APS 31.3 #85 of 220 Archive leaderboard report
Object Detection COCO minival DN-Deformable-DETR-R50++ Params (M) 47 #85 of 220 Archive leaderboard report
Object Detection COCO minival DN-Deformable-DETR-R50++ box AP 49.5 #85 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