Papers › End-to-End Object Detection with Transformers

End-to-End Object Detection with Transformers

26 May 2020ECCV 2020 8arXiv:2005.12872archive 2025-07-28

Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko

We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge about the task. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons about the relations of the objects and the global image context to directly output the final set of predictions in parallel. The new model is conceptually simple and does not require a specialized library, unlike many other modern detectors. DETR demonstrates accuracy and run-time performance on par with the well-established and highly-optimized Faster RCNN baseline on the challenging COCO object detection dataset. Moreover, DETR can be easily generalized to produce panoptic segmentation in a unified manner. We show that it significantly outperforms competitive baselines. Training code and pretrained models are available at https://github.com/facebookresearch/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 92 code samples harvested from 13 repositories linked to this paper: 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. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 89 samples from 12 repositories, 68 ran (61 with no instrument failure; 7 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 11 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 70 samples that ran has no recorded date.

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

facebookresearch/detr officialmentioned in paperpytorchApache-2.0Syntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
DataXujing/TensorRT-DETR mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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
JunnYu/x-transformers-paddle mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer V2: Scaling Up Capacity and Resolution (arXiv:2111.09883; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
KostadinovShalon/UAVDetectionTrackingBenchmark mentioned on GitHubpytorchSyntology: not harvested report
LKLQQ/detr mentioned on GitHubmindsporeApache-2.0Syntology: 13 samples, 12 ran (1 instrument-failed) · 1 unverified report
Leonardo-Blanger/detr_tensorflow mentioned on GitHubtfSyntology: 16 samples, 11 ran (0 instrument-failed) · 5 unverified report
Li-ai-cell/Interpretation_DETR mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
Saloni1Parekh609/MIDAS mentioned on GitHubpytorchSyntology: not harvested report
Visual-Behavior/aloception mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deformable DETR: Deformable Transformers for End-to-End Object Detection (arXiv:2010.04159; that paper's own run record: 37 ran (of which 9 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 3 violated, 20 with no contract checked; 13 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
Visual-Behavior/detr-tensorflow mentioned on GitHubtfSyntology: 14 samples, 7 ran (0 instrument-failed) · 7 unverified report
abdksyed/DETR mentioned on GitHubpytorchMITSyntology: not harvested report
ananyahjha93/swav mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
benywon/ChiQA mentioned on GitHubpytorchSyntology: not harvested report
clive819/Modified-DETR mentioned on GitHubpytorchSyntology: 16 samples, 15 ran (2 instrument-failed) · 1 unverified report
facebookresearch/swav mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
hsfzxjy/swavx mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Clustering for Unsupervised Learning of Visual Features (arXiv:1807.05520; that paper's own run record: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified) and Self-labelling via simultaneous clustering and representation learning (arXiv:1911.05371; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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
longbai1006/surgical-vqla mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question... (arXiv:2305.11692; that paper's own run record: 7 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; 5 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
marcusnerva/hmn mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
mlpc-ucsd/PRTR mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
pranavjadhav001/detr_keras mentioned on GitHubtfSyntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified report
tahmid0007/DETR_FineTune mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
w-sugar/prtr mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
ywsyws/FormationSimplon20200622dlKeras mentioned on GitHubSyntology: not harvested report
2023-MindSpore-1/ms-code-69 mindsporeApache-2.0Syntology: not harvested report
2024-MindSpore-1/Code2 mindsporeSyntology: not harvested report
BR-IDL/PaddleViT paddleSyntology: not harvested report
EmGarr/kerod tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Feature Pyramid Networks for Object Detection (arXiv:1612.03144; that paper's own run record: 33 ran (of which 9 constructed an object rather than computing a result; 28 with no instrument failure: 4 honoured, 0 violated, 24 with no contract checked; 5 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
alibaba/EasyCV pytorchSyntology: 14 samples, 13 ran (2 instrument-failed) · 1 unverified report
jiaxu-Zhu/DETR mindsporeSyntology: not harvested 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
tensorflow/models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
xiuyu0000/papers_with_examples mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Lite-HRNet: A Lightweight High-Resolution Network (arXiv:2104.06403; that paper's own run record: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/DETR mindsporeSyntology: not harvested report
gitlab.com/birder/birder pytorchSyntology: not harvested 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

92 samples harvested: 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. “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 · honoured contract
1ran · violated contract
8ran · our draft was wrong
59ran
22unverified

Licence: 19 of the 92 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 13 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 15 samples 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.

facebookresearch/detr official repository 3 samples, 2 ran (1 instrument-failed) · 1 unverified
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 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
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 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
build_transformer in 62 papers models/transformer.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 302ec916d91b12a8 · report
DataXujing/TensorRT-DETR community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DETR in 5 papers model/detr.py ran Apache-2.0 (permissive) · a08f693477433cf5 · report fixture: returned DETR · level recorded 2026-09-22
LKLQQ/detr community (archive-listed) 13 samples, 12 ran (1 instrument-failed) · 1 unverified
area_box_grad src/grad_ops.py ran fingerprinted Apache-2.0 (permissive) · 439ca3d20ddd3507 · report fixture: signature box:ndarray/2/float · returned ndarray · level recorded 2026-09-24
box_cxcywh_to_xyxy in 60 papers src/box_ops.py ran fingerprinted Apache-2.0 (permissive) · 074307e51146fa09 · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-24
box_xyxy_to_cxcywh in 37 papers src/box_ops.py ran fingerprinted Apache-2.0 (permissive) · dbb0d0f90ff599c4 · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-24
box_xyxy_to_xywh in 19 papers src/box_ops.py ran fingerprinted Apache-2.0 (permissive) · c7dc3cdd056cc5f7 · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-24
grad_xywh_to_cxcy src/grad_ops.py ran fingerprinted Apache-2.0 (permissive) · b825001fb2f9656b · report fixture: signature arr:ndarray/2/float · returned ndarray · level recorded 2026-09-24
merge in 85 papers model_utils/config.py ran · our draft was wrong Apache-2.0 (permissive) · b9e24c3e3e0e88a7 · report fixture: signature args:Namespace/0/?, cfg:dict/0/? · returned dict · level recorded 2026-09-22
numpy_one_hot src/criterion.py ran Apache-2.0 (permissive) · ecf96aec72671319 · report fixture: signature targets:ndarray/2/int, num_classes:int/0/int · returned ndarray · level recorded 2026-09-24
pad_image_to_max_size src/dataset.py ran fingerprinted Apache-2.0 (permissive) · d22f5a2cc9a9741d · report fixture: signature img:ndarray/3/float, max_size:int/0/int · returned tuple · level recorded 2026-09-24
parse_cli_to_yaml in 29 papers model_utils/config.py ran Apache-2.0 (permissive) · 85b09f6f153fd5d3 · report fixture: signature parser:ArgumentParser/0/?, cfg:dict/0/?, helper:dict/0/?, choices:dict/0/?, cfg_path:str/0/str · returned Namespace · level recorded 2026-09-25
parse_yaml in 32 papers model_utils/config.py ran Apache-2.0 (permissive) · 96a9939953d5992d · report fixture: signature yaml_path:str/0/str · returned tuple · level recorded 2026-09-25
prepare_data in 87 papers src/dataset.py ran Apache-2.0 (permissive) · fa31404b74c4548c · report fixture: signature image:ndarray/3/int, target:dict/0/? · returned tuple · level recorded 2026-09-24
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
src/matcher.py ran fingerprinted Apache-2.0 (permissive) · 4c36dfd151b487bb · report fixture: signature arr:ndarray/2/float, axis:NoneType/0/? · returned ndarray · level recorded 2026-09-24
dres_dwh src/grad_ops.py unverified Apache-2.0 (permissive) · f111786e2550d75b · report
Leonardo-Blanger/detr_tensorflow community (archive-listed) 16 samples, 11 ran (0 instrument-failed) · 5 unverified
BottleNeck detr_tensorflow/models/detr.py ran MIT (permissive) · 166ac89882b932d6 · report fixture: returned BottleNeck · level recorded 2026-09-22
DecoderLayer in 43 papers detr_tensorflow/models/detr.py ran MIT (permissive) · af5a7f149644b25e · report fixture: returned DecoderLayer · level recorded 2026-09-22
EncoderLayer in 73 papers detr_tensorflow/models/detr.py ran MIT (permissive) · e386b72d977ac828 · report fixture: returned EncoderLayer · level recorded 2026-09-22
FixedEmbedding in 6 papers detr_tensorflow/models/detr.py ran MIT (permissive) · ec7f81ffdbd55a8d · report fixture: returned FixedEmbedding · level recorded 2026-09-22
Linear in 127 papers detr_tensorflow/models/detr.py ran MIT (permissive) · c8278aeb1cd2c753 · report fixture: returned Linear · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
detr_tensorflow/models/detr.py ran MIT (permissive) · d81ff048a53b3958 · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
PositionEmbeddingSine in 21 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
detr_tensorflow/models/detr.py ran MIT (permissive) · 30bbae6bd017a72b · report fixture: returned PositionEmbeddingSine · level recorded 2026-09-22
ResNet50Backbone detr_tensorflow/models/detr.py ran MIT (permissive) · 4ccf2425db7e2edf · report fixture: returned ResNet50Backbone · level recorded 2026-09-22
ResNetBase detr_tensorflow/models/detr.py ran MIT (permissive) · 4d5b0985a478ce49 · report fixture: returned ResNetBase · level recorded 2026-09-22
ResidualBlock in 100 papers detr_tensorflow/models/detr.py ran MIT (permissive) · 71f64d952481419d · report fixture: returned ResidualBlock · level recorded 2026-09-22
cxcywh2xyxy detr_tensorflow/models/detr.py ran · honoured contract fingerprinted MIT (permissive) · 51f528c6568ec2bc · report fixture: signature boxes:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
DETR in 5 papers detr_tensorflow/models/detr.py unverified MIT (permissive) · 76939fc80775bf4c · report
FrozenBatchNorm2D detr_tensorflow/models/detr.py unverified MIT (permissive) · eac14a02a01c9fef · report
Transformer in 173 papers detr_tensorflow/models/detr.py unverified MIT (permissive) · 8788012951b03bcd · report
TransformerDecoder in 49 papers detr_tensorflow/models/detr.py unverified MIT (permissive) · b500f1a1d4c6a31b · report
TransformerEncoder in 96 papers detr_tensorflow/models/detr.py unverified MIT (permissive) · f75019a62f5a7aac · report
Li-ai-cell/Interpretation_DETR community (archive-listed) 5 samples, 5 ran (2 instrument-failed) · 0 unverified
DeformableDETR in 7 papers models/deformable_detr.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 6e9d22c76a65085c · report fixture: returned DeformableDETR · level recorded 2026-09-22
MLP in 375 papers models/deformable_detr.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 38f2143f420f7378 · report fixture: returned MLP · level recorded 2026-09-22
NestedTensor in 24 papers models/deformable_detr.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · b3bc5ccabebb6be8 · report fixture: returned NestedTensor · level recorded 2026-09-22
_get_clones in 28 papers models/deformable_detr.py ran · our draft was wrong Apache-2.0 (permissive) · 2987ca2d1c68e0cd · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
nested_tensor_from_tensor_list in 60 papers models/deformable_detr.py ran · our draft was wrong Apache-2.0 (permissive) · 58a69a8a71330322 · report fixture: signature tensor_list:list/1/Tensor · returned NestedTensor · level recorded 2026-09-22
Visual-Behavior/detr-tensorflow community (archive-listed) 14 samples, 7 ran (0 instrument-failed) · 7 unverified
BottleNeck detr_tf/networks/detr.py ran MIT (permissive) · 3a7615caf1c19859 · report fixture: returned BottleNeck · level recorded 2026-09-22
FixedEmbedding in 6 papers detr_tf/networks/detr.py ran MIT (permissive) · 14483127db755736 · report fixture: returned FixedEmbedding · level recorded 2026-09-22
Linear in 127 papers detr_tf/networks/detr.py ran MIT (permissive) · b1d65c380b6c2141 · report fixture: returned Linear · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
detr_tf/networks/detr.py ran MIT (permissive) · 595c977770d20ea9 · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
ResNet50Backbone detr_tf/networks/detr.py ran MIT (permissive) · f6fb3cc7cc9b79c8 · report fixture: returned ResNet50Backbone · level recorded 2026-09-22
ResNetBase detr_tf/networks/detr.py ran MIT (permissive) · 03e8c57dd4bc7e84 · report fixture: returned ResNetBase · level recorded 2026-09-22
ResidualBlock in 100 papers detr_tf/networks/detr.py ran MIT (permissive) · 4530f047f9d8c2a8 · report fixture: returned ResidualBlock · level recorded 2026-09-22
DETR in 5 papers detr_tf/networks/detr.py unverified MIT (permissive) · 3ef18650a72fd6e5 · report
DecoderLayer in 43 papers detr_tf/networks/detr.py unverified MIT (permissive) · 8f0652e50cf5e88e · report
EncoderLayer in 73 papers detr_tf/networks/detr.py unverified MIT (permissive) · 365feef25cdfddae · report
FrozenBatchNorm2D detr_tf/networks/detr.py unverified MIT (permissive) · 489904fdbc4744b8 · report
Transformer in 173 papers detr_tf/networks/detr.py unverified MIT (permissive) · 96eb11ad4f60883d · report
TransformerDecoder in 49 papers detr_tf/networks/detr.py unverified MIT (permissive) · c8dfba0da8dc5339 · report
TransformerEncoder in 96 papers detr_tf/networks/detr.py unverified MIT (permissive) · e6b904745326551b · report
clive819/Modified-DETR community (archive-listed) 16 samples, 15 ran (2 instrument-failed) · 1 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · e7741ce58fdf0670 · report fixture: returned ConvBlock · level recorded 2026-09-22
DenseBlock in 6 papers models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · dc4458eeece80ec3 · report fixture: returned DenseBlock · level recorded 2026-09-22
DenseNet in 5 papers models/detr.py ran no licence file found · pointer only · 2a3f28612aea2e52 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Joiner in 6 papers models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 516138a354d8a8b6 · report fixture: returned Joiner · level recorded 2026-09-22
MLP in 375 papers models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3465a25340dd9ced · report fixture: returned MLP · level recorded 2026-09-22
PositionEmbeddingSine in 21 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3f7df5ae93d75f73 · report fixture: returned PositionEmbeddingSine · level recorded 2026-09-22
Transformer in 173 papers models/detr.py ran · metamorphic tier: deterministic no licence file found · pointer only · e7754ceb0d3ebd3f · report fixture: returned Transformer · level recorded 2026-09-22
TransformerDecoder in 49 papers models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 015ab94ccd1059d4 · report fixture: returned TransformerDecoder · level recorded 2026-09-22
TransformerDecoderLayer in 45 papers models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · e6df50cb4054a21d · report fixture: returned TransformerDecoderLayer · level recorded 2026-09-22
TransformerEncoder in 96 papers models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 6085c3edb73b1432 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
TransformerEncoderLayer in 90 papers models/detr.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3e3613a79dc6d21d · report fixture: returned TransformerEncoderLayer · level recorded 2026-09-22
TransitionLayer models/detr.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8cf47b464bc0f064 · report fixture: returned TransitionLayer · level recorded 2026-09-22
buildBackbone models/detr.py ran · our draft was wrong no licence file found · pointer only · 85412aff426c3960 · report fixture: signature args:Args/0/? · returned Joiner · level recorded 2026-09-22
getClones models/detr.py ran · our draft was wrong no licence file found · pointer only · e2883ab685be2301 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
withPosEmbed models/detr.py ran · honoured contract fingerprinted no licence file found · pointer only · dfee3988cadd459d · report fixture: signature tensor:Tensor/2/float, pos:Tensor/2/float · returned Tensor · level recorded 2026-09-22
DETR in 5 papers models/detr.py unverified no licence file found · pointer only · b623cf8db82439f6 · report
marcusnerva/hmn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
HungarianMatcher in 5 papers models/hungary.py ran · metamorphic tier: deterministic MIT (permissive) · cc9bf980c4abd872 · report fixture: signature salient_objects:Tensor/3/float, nouns_dict_list:list/1/dict · returned list · level recorded 2026-09-22
mlpc-ucsd/PRTR community (archive-listed) 1 sample, 0 ran · 1 unverified
Transformer in 173 papers two_stage/lib/models/transformer.py unverified Apache-2.0 (permissive) · 7507c26a9f353a7a · report
pranavjadhav001/detr_keras community (archive-listed) 6 samples, 3 ran (0 instrument-failed) · 3 unverified
DecoderLayer in 43 papers detr/detr.py ran MIT (permissive) · 915b67b9468a4470 · report fixture: returned DecoderLayer · level recorded 2026-09-22
Encoder in 278 papers detr/detr.py ran MIT (permissive) · afa0a513d38b46bc · report fixture: returned Encoder · level recorded 2026-09-22
EncoderLayer in 73 papers detr/detr.py ran MIT (permissive) · 2aa3afdcd66d8888 · report fixture: returned EncoderLayer · level recorded 2026-09-22
Decoder in 210 papers detr/detr.py unverified MIT (permissive) · 7cde3a2c2086bf81 · report
Detr detr/detr.py unverified MIT (permissive) · 1fff7933c81752a0 · report
Transformer in 173 papers detr/detr.py unverified MIT (permissive) · f8f411f90ea10f1b · report
tahmid0007/DETR_FineTune community (archive-listed) 1 sample, 0 ran · 1 unverified
DETR in 5 papers models/detr.py unverified Apache-2.0 (permissive) · 8bca9001c145c378 · report
w-sugar/prtr community (archive-listed) 1 sample, 0 ran · 1 unverified
Transformer in 173 papers two_stage/lib/models/transformer.py unverified Apache-2.0 (permissive) · 3b1c3de9b6a7bc34 · report
alibaba/EasyCV community (archive-listed) 14 samples, 13 ran (2 instrument-failed) · 1 unverified
BaseError easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · 6f3e4e43ff039081 · report fixture: returned BaseError · level recorded 2026-09-22
KeyError easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · cd97bea208feabb0 · report fixture: returned KeyError · level recorded 2026-09-22
MLP in 375 papers easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · 61eefc8cd1d96134 · report fixture: returned MLP · level recorded 2026-09-22
Registry in 34 papers easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · c9a86343969e354f · report fixture: returned Registry · level recorded 2026-09-22
RuntimeError easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · 871157f97c91d2cb · report fixture: returned RuntimeError · level recorded 2026-09-22
SinePositionalEncoding easycv/models/detection/detectors/detr/detr_transformer.py ran fingerprinted Apache-2.0 (permissive) · a47d44d68f6ee645 · report fixture: signature mask:Tensor/3/float · returned Tensor · level recorded 2026-09-24
TransformerDecoder in 49 papers easycv/models/detection/detectors/detr/detr_transformer.py ran fingerprinted Apache-2.0 (permissive) · ee78371dbc19ce86 · report fixture: returned TransformerDecoder · level recorded 2026-09-22
TransformerDecoderLayer in 45 papers easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · 9c120638dc644120 · report fixture: returned TransformerDecoderLayer · level recorded 2026-09-22
TransformerEncoder in 96 papers easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · 8a4db2ad3894b67c · report fixture: returned TransformerEncoder · level recorded 2026-09-22
TransformerEncoderLayer in 90 papers easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · 526d67b8881712d6 · report fixture: returned TransformerEncoderLayer · level recorded 2026-09-22
TypeError easycv/models/detection/detectors/detr/detr_transformer.py ran Apache-2.0 (permissive) · b1bd1c1bd350e556 · report fixture: returned TypeError · level recorded 2026-09-22
_get_activation_fn in 21 papers easycv/models/detection/detectors/detr/detr_transformer.py ran · our draft was wrong Apache-2.0 (permissive) · 184de768ec89ba57 · report fixture: signature activation:str/0/str · returned function · level recorded 2026-09-22
_get_clones in 28 papers easycv/models/detection/detectors/detr/detr_transformer.py ran · our draft was wrong Apache-2.0 (permissive) · a044a67f7fbc0842 · report fixture: signature module:callable/0/?, N:int/0/int, layer_share:bool/0/bool · returned ModuleList · level recorded 2026-09-22
DetrTransformer easycv/models/detection/detectors/detr/detr_transformer.py unverified Apache-2.0 (permissive) · 6c3e4ed3f765415b · 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.

11 assemblies on this paper: 11 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

11 sibling assemblies for 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 DETR (graph method: DETR). 16 bricks; individually on a fixture: 11 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DETR entry · level 0 · unverified · 76939fc80775bf4c
  2. FixedEmbedding helper · level 1 · ran · ec7f81ffdbd55a8d
  3. Linear helper · level 1 · ran · c8278aeb1cd2c753
  4. PositionEmbeddingSine model · level 1 · ran · 30bbae6bd017a72b
  5. ResNet50Backbone helper · level 1 · ran · 4ccf2425db7e2edf
  6. Transformer model · level 0 · unverified · 8788012951b03bcd
  7. cxcywh2xyxy helper · level 1 · ran · honoured contract · 51f528c6568ec2bc
  8. ResNetBase model · level 1 · ran · 4d5b0985a478ce49
  9. ResidualBlock helper · level 1 · ran · 71f64d952481419d
  10. TransformerDecoder helper · level 0 · unverified · b500f1a1d4c6a31b
  11. TransformerEncoder helper · level 0 · unverified · f75019a62f5a7aac
  12. FrozenBatchNorm2D helper · level 0 · unverified · eac14a02a01c9fef
  13. BottleNeck helper · level 1 · ran · 166ac89882b932d6
  14. DecoderLayer helper · level 1 · ran · af5a7f149644b25e
  15. EncoderLayer helper · level 1 · ran · e386b72d977ac828
  16. MultiHeadAttention helper · level 1 · ran · d81ff048a53b3958

harvested Assembly for DETR (graph method: DETR). 16 bricks; individually on a fixture: 15 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DETR entry · level 0 · unverified · b623cf8db82439f6
  2. MLP helper · level 1 · ran · 3465a25340dd9ced
  3. Transformer model · level 1 · ran · e7754ceb0d3ebd3f
  4. buildBackbone model · level 1 · ran · our draft was wrong · 85412aff426c3960
  5. TransformerDecoder helper · level 1 · ran · 015ab94ccd1059d4
  6. TransformerDecoderLayer helper · level 1 · ran · e6df50cb4054a21d
  7. TransformerEncoder helper · level 1 · ran · 6085c3edb73b1432
  8. TransformerEncoderLayer helper · level 1 · ran · 3e3613a79dc6d21d
  9. DenseNet helper · level 1 · ran · 2a3f28612aea2e52
  10. Joiner helper · level 1 · ran · 516138a354d8a8b6
  11. PositionEmbeddingSine helper · level 1 · ran · 3f7df5ae93d75f73
  12. getClones helper · level 1 · ran · our draft was wrong · e2883ab685be2301
  13. withPosEmbed helper · level 1 · ran · honoured contract · dfee3988cadd459d
  14. DenseBlock helper · level 1 · ran · dc4458eeece80ec3
  15. TransitionLayer helper · level 1 · ran · 8cf47b464bc0f064
  16. ConvBlock helper · level 1 · ran · e7741ce58fdf0670

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

one of 11 siblings

  1. DeformableDETR entry · level 1 · ran · 6e9d22c76a65085c
  2. MLP helper · level 1 · ran · 38f2143f420f7378
  3. NestedTensor helper · level 1 · ran · b3bc5ccabebb6be8
  4. _get_clones helper · level 1 · ran · our draft was wrong · 2987ca2d1c68e0cd
  5. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 83c03ceb1307c6c4
  6. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 58a69a8a71330322
  7. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1

harvested Assembly for DETR (graph method: DETR). 7 bricks; individually on a fixture: 6 ran (of which 4 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) · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. Transformer entry · level 0 · unverified · 7507c26a9f353a7a
  2. TransformerDecoder model · level 1 · ran · 46e93b05a334499a
  3. TransformerDecoderLayer model · level 1 · ran · df37859c9b2a3024
  4. TransformerEncoder model · level 1 · ran · ec86d33233d305b6
  5. TransformerEncoderLayer model · level 1 · ran · 110d117a309e1201
  6. _get_clones helper · level 1 · ran · our draft was wrong · 133b1e9e564b059c
  7. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08

harvested Assembly for DETR (graph method: DETR). 15 bricks; individually on a fixture: 8 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified; every one of the 8 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 11 siblings

  1. DETR entry · level 0 · unverified · 3ef18650a72fd6e5
  2. FixedEmbedding helper · level 1 · ran · 14483127db755736
  3. Linear helper · level 1 · ran · b1d65c380b6c2141
  4. PositionEmbeddingSine helper · level 1 · ran · 30bbae6bd017a72b
  5. ResNet50Backbone helper · level 1 · ran · f6fb3cc7cc9b79c8
  6. Transformer model · level 0 · unverified · 96eb11ad4f60883d
  7. ResNetBase helper · level 1 · ran · 03e8c57dd4bc7e84
  8. ResidualBlock helper · level 1 · ran · 4530f047f9d8c2a8
  9. TransformerDecoder helper · level 0 · unverified · c8dfba0da8dc5339
  10. TransformerEncoder helper · level 0 · unverified · e6b904745326551b
  11. FrozenBatchNorm2D helper · level 0 · unverified · 489904fdbc4744b8
  12. BottleNeck helper · level 1 · ran · 3a7615caf1c19859
  13. DecoderLayer helper · level 0 · unverified · 8f0652e50cf5e88e
  14. EncoderLayer helper · level 0 · unverified · 365feef25cdfddae
  15. MultiHeadAttention model · level 1 · ran · 595c977770d20ea9

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

one of 11 siblings

  1. DETR entry · level 1 · ran · a08f693477433cf5
  2. MLP helper · level 1 · ran · d71ab24dd4408288
  3. NestedTensor helper · level 1 · ran · b636bcda4557023e
  4. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · a78bbd4466ce14cd
  5. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  6. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 2c9ff7cc9c4634f9

harvested Assembly for DETR (graph method: DETR). 13 bricks; individually on a fixture: 9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 9 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 11 siblings

  1. Detr entry · level 0 · unverified · 1fff7933c81752a0
  2. FixedEmbedding helper · level 1 · ran · ec7f81ffdbd55a8d
  3. PositionEmbeddingSine helper · level 1 · ran · 30bbae6bd017a72b
  4. ResNet50Backbone model · level 1 · ran · 4ccf2425db7e2edf
  5. Transformer model · level 0 · unverified · f8f411f90ea10f1b
  6. ResNetBase helper · level 1 · ran · 4d5b0985a478ce49
  7. ResidualBlock helper · level 1 · ran · 71f64d952481419d
  8. Decoder helper · level 0 · unverified · 7cde3a2c2086bf81
  9. Encoder helper · level 1 · ran · afa0a513d38b46bc
  10. FrozenBatchNorm2D helper · level 0 · unverified · eac14a02a01c9fef
  11. BottleNeck helper · level 1 · ran · 166ac89882b932d6
  12. DecoderLayer helper · level 1 · ran · 915b67b9468a4470
  13. EncoderLayer helper · level 1 · ran · 2aa3afdcd66d8888

harvested Assembly for DETR (graph method: DETR). 14 bricks; individually on a fixture: 13 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DetrTransformer entry · level 0 · unverified · 6c3e4ed3f765415b
  2. SinePositionalEncoding helper · level 1 · ran · a47d44d68f6ee645
  3. TransformerDecoder model · level 1 · ran · ee78371dbc19ce86
  4. TransformerDecoderLayer model · level 1 · ran · 9c120638dc644120
  5. TransformerEncoder helper · level 1 · ran · 8a4db2ad3894b67c
  6. TransformerEncoderLayer helper · level 1 · ran · 526d67b8881712d6
  7. _get_clones helper · level 1 · ran · our draft was wrong · a044a67f7fbc0842
  8. _get_activation_fn helper · level 1 · ran · our draft was wrong · 184de768ec89ba57
  9. MLP helper · level 1 · ran · 61eefc8cd1d96134
  10. RuntimeError helper · level 1 · ran · 871157f97c91d2cb
  11. BaseError helper · level 1 · ran · 6f3e4e43ff039081
  12. KeyError helper · level 1 · ran · cd97bea208feabb0
  13. Registry helper · level 1 · ran · c9a86343969e354f
  14. TypeError helper · level 1 · ran · b1bd1c1bd350e556

harvested Assembly for DETR (graph method: DETR). 6 bricks; individually on a fixture: 4 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; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DETR entry · level 0 · unverified · 8bca9001c145c378
  2. MLP helper · level 1 · ran · d71ab24dd4408288
  3. NestedTensor helper · level 1 · ran · b636bcda4557023e
  4. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 9277ea2a21aca6f8
  5. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  6. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 0ff86335d5b895ad

harvested Assembly for DETR (graph method: DETR). 7 bricks; individually on a fixture: 6 ran (of which 4 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) · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. Transformer entry · level 0 · unverified · 3b1c3de9b6a7bc34
  2. TransformerDecoder model · level 1 · ran · 46e93b05a334499a
  3. TransformerDecoderLayer model · level 1 · ran · df37859c9b2a3024
  4. TransformerEncoder model · level 1 · ran · ec86d33233d305b6
  5. TransformerEncoderLayer model · level 1 · ran · 110d117a309e1201
  6. _get_clones helper · level 1 · ran · our draft was wrong · 133b1e9e564b059c
  7. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08

harvested Assembly for DETR (graph method: DETR). 1 brick; individually on a fixture: 1 ran (of which 0 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 assembly has not been run end-to-end.

one of 11 siblings

  1. HungarianMatcher entry · level 1 · ran · cc9bf980c4abd872

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="2005.12872") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

2D Object DetectionDecoderObjectObject DetectionPanoptic SegmentationReal-Time Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival DETR-DC5 (ResNet-101) AP50 64.7 #120 of 220 Archive leaderboard report
Object Detection COCO minival DETR-DC5 (ResNet-101) AP75 47.7 #120 of 220 Archive leaderboard report
Object Detection COCO minival DETR-DC5 (ResNet-101) APL 62.3 #120 of 220 Archive leaderboard report
Object Detection COCO minival DETR-DC5 (ResNet-101) APM 49.5 #120 of 220 Archive leaderboard report
Object Detection COCO minival DETR-DC5 (ResNet-101) APS 23.7 #120 of 220 Archive leaderboard report
Object Detection COCO minival DETR-DC5 (ResNet-101) box AP 44.9 #120 of 220 Archive leaderboard report
Object Detection COCO minival Faster RCNN-R101-FPN+ AP50 63.9 #136 of 220 Archive leaderboard report
Object Detection COCO minival Faster RCNN-R101-FPN+ AP75 47.8 #136 of 220 Archive leaderboard report
Object Detection COCO minival Faster RCNN-R101-FPN+ APL 56 #136 of 220 Archive leaderboard report
Object Detection COCO minival Faster RCNN-R101-FPN+ APM 48.1 #136 of 220 Archive leaderboard report
Object Detection COCO minival Faster RCNN-R101-FPN+ APS 27.2 #136 of 220 Archive leaderboard report
Object Detection COCO minival Faster RCNN-R101-FPN+ box AP 44 #136 of 220 Archive leaderboard report
Object Detection COCO-O DETR (ResNet-50) Average mAP 17.1 #36 of 45 Archive leaderboard report
Object Detection COCO-O DETR (ResNet-50) Effective Robustness -1.82 #36 of 45 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) AP 33 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) PQ 45.1 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) PQst 37 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) PQth 50.5 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) RQ 55.5 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) RQst 46 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) RQth 61.7 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) SQ 79.9 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) SQst 78.5 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival DETR-R101 (ResNet-101) SQth 80.9 #25 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ AP 39.7 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ PQ 44.1 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ PQst 33.6 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ PQth 51.0 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ RQ 53.3 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ RQst 42.1 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ RQth 60.6 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ SQ 79.5 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ SQst 74.0 #27 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival PanopticFPN++ SQth 83.2 #27 of 31 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) Faster RCNN-FPN+ FPS (V100, b=1) 26 #74 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) Faster RCNN-FPN+ box AP 42 #74 of 82 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 LayerReLUResidual 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