Papers › Conditional DETR for Fast Training Convergence

Conditional DETR for Fast Training Convergence

13 Aug 2021ICCV 2021 10arXiv:2108.06152archive 2025-07-28

Depu Meng, Xiaokang Chen, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun, Jingdong Wang

The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings for localizing the four extremities and predicting the box, which increases the need for high-quality content embeddings and thus the training difficulty. Our approach, named conditional DETR, learns a conditional spatial query from the decoder embedding for decoder multi-head cross-attention. The benefit is that through the conditional spatial query, each cross-attention head is able to attend to a band containing a distinct region, e.g., one object extremity or a region inside the object box. This narrows down the spatial range for localizing the distinct regions for object classification and box regression, thus relaxing the dependence on the content embeddings and easing the training. Empirical results show that conditional DETR converges 6.7x faster for the backbones R50 and R101 and 10x faster for stronger backbones DC5-R50 and DC5-R101. Code is available at https://github.com/Atten4Vis/ConditionalDETR.

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 9 code samples harvested from 2 repositories linked to this paper: 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. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 5 ran (2 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (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.

atten4vis/conditionaldetr officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 5 ran (3 instrument-failed) · 3 unverified report
IDEA-Research/detrex mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
yangyucheng000/University mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (arXiv:2409.12191; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 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

9 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
1ran
3unverified

Licence: 4 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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”. “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.

atten4vis/conditionaldetr official repository 8 samples, 5 ran (3 instrument-failed) · 3 unverified
convert_to_xywh in 26 papers datasets/coco_eval.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · f31a58bf6457ced5 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-22
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/segmentation.py ran · violated contract fingerprinted Apache-2.0 (permissive) · ac8fe530cdad4d8c · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int · returned Tensor · level recorded 2026-09-22
evaluate in 514 papers datasets/coco_eval.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · fe0ddcc2d420c9a0 · report fixture: signature self:MockCOCOEval/0/? · returned tuple · level recorded 2026-09-22
gen_sineembed_for_position in 29 papers models/transformer.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · d573d92393e20123 · report fixture: signature pos_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-25
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/segmentation.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
ConditionalDETR models/conditional_detr.py unverified Apache-2.0 (permissive) · 630f5aa14fbee6c6 · report
build_transformer in 62 papers models/transformer.py unverified Apache-2.0 (permissive) · bf149877606cbfba · report
multi_head_attention_forward in 73 papers models/attention.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · f09175b0f39f0ad0 · report
IDEA-Research/detrex community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ConditionalCrossAttention detrex/layers/attention.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 47b02db49bdfd76e · report fixture: returned ConditionalCrossAttention · level recorded 2026-09-22

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 Conditional 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 Conditional DETR (graph method: Conditional DETR). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. ConditionalCrossAttention entry · level 1 · ran · 47b02db49bdfd76e

harvested Assembly for Conditional DETR (graph method: Conditional 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 2 siblings

  1. ConditionalDETR entry · level 0 · unverified · 630f5aa14fbee6c6
  2. MLP helper · level 1 · ran · d71ab24dd4408288
  3. NestedTensor helper · level 1 · ran · b636bcda4557023e
  4. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 83c03ceb1307c6c4
  5. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 9277ea2a21aca6f8
  6. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  7. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 0ff86335d5b895ad

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="2108.06152") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival Conditional DETR-DC5-R101 AP50 66.8 #110 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R101 AP75 49.5 #110 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R101 APL 63.3 #110 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R101 APM 50.3 #110 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R101 APS 27.2 #110 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R101 Params (M) 63 #110 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R101 box AP 45.9 #110 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R50 AP50 65.4 #116 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R50 AP75 48.5 #116 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R50 APL 62.2 #116 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R50 APM 49 #116 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R50 APS 25.3 #116 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R50 Params (M) 44 #116 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-DC5-R50 box AP 45.1 #116 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R101 AP50 65.6 #127 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R101 AP75 47.5 #127 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R101 APL 63.6 #127 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R101 APM 48.4 #127 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R101 APS 23.6 #127 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R101 Params (M) 63 #127 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R101 box AP 44.5 #127 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R50 AP50 64 #147 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R50 AP75 45.7 #147 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R50 APL 61.5 #147 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R50 APM 46.7 #147 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R50 APS 22.7 #147 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R50 Params (M) 44 #147 of 220 Archive leaderboard report
Object Detection COCO minival Conditional DETR-R50 box AP 43 #147 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