Papers › EfficientDet: Scalable and Efficient Object Detection

EfficientDet: Scalable and Efficient Object Detection

20 Nov 2019CVPR 2020 6arXiv:1911.09070archive 2025-07-28

Mingxing Tan, Ruoming Pang, Quoc V. Le

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency. First, we propose a weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multiscale feature fusion; Second, we propose a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time. Based on these optimizations and better backbones, we have developed a new family of object detectors, called EfficientDet, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with single model and single-scale, our EfficientDet-D7 achieves state-of-the-art 55.1 AP on COCO test-dev with 77M parameters and 410B FLOPs, being 4x - 9x smaller and using 13x - 42x fewer FLOPs than previous detectors. Code is available at https://github.com/google/automl/tree/master/efficientdet.

PaperPDFConference PDFCodeCode Syntology ran

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

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

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

Code

Syntology 70 code samples harvested from 13 repositories linked to this paper: 55 ran (of which 1 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 69 samples from 12 repositories, 54 ran (48 with no instrument failure; 6 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 55 samples that ran has no recorded date.

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

google/automl officialmentioned in papertfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
DataXujing/EfficientDet_pytorch mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
Guillem96/efficientdet-tf mentioned on GitHubtfGPL-3.0Syntology: not harvested report
HardLaugh/EfficientDet-bifpn mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
JagadishSivakumar/GlobalWheatDetection mentioned on GitHubSyntology: not harvested report
JensSettelmeier/EfficientDet-DeepSORT-Tracker mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
Jintao-Huang/EfficientDet_PyTorch mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 6 ran (1 instrument-failed) · 4 unverified report
Luckygyana/Invo-AI mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
ManfredGonzalez/multispectral-pineapple-detection mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Manugoyal12345/Yet-Another-EfficientDet-Pytorch mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
Mind23-2/MindCode-36 mentioned on GitHubmindsporeSyntology: not harvested report
Mind23-2/MindCode-37 mentioned on GitHubmindsporeSyntology: not harvested report
SharifElfouly/easy-model-zoo mentioned on GitHubpytorchMITSyntology: 10 samples, 9 ran (1 instrument-failed) · 1 unverified report
djkim3/Yet-Another-EfficientDet-Pytorch mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
edwardning/Pytorch-EfficientDet-ModelArts mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
fgabel/EfficientDet-DeepSORT-Tracker mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
google/automl mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
irvankadhafi/Burnt-PCB-Object-Detection mentioned on GitHubtfMITSyntology: not harvested report
jahongir7174/EfficientDet-tf mentioned on GitHubtfSyntology: not harvested report
kochlisGit/Custom-Small-Logo-Detection mentioned on GitHubtfSyntology: not harvested report
kochlisGit/LogoLens mentioned on GitHubtfSyntology: not harvested report
kushaswani/LitterNet-webapp mentioned on GitHubpytorchMITSyntology: not harvested report
lvweiwolf/efficientdet mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
murdockhou/Yet-Another-EfficientDet-Pytorch-Convert-ONNX-TVM mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
ravi02512/efficientdet-keras mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
rwightman/efficientdet-pytorch mentioned on GitHubpytorchSyntology: not harvested report
sara-nl/SURF-deeplab mentioned on GitHubtfSyntology: not harvested report
sara-nl/SURF-segmentation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified); nothing checks that they implement this paper's method. report
sdkchris/Exercise-Sheet-1 mentioned on GitHubtfSyntology: not harvested report
sevakon/efficientdet mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (1 instrument-failed) · 1 unverified report
shivam-raj/detector mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
signatrix/efficientdet mentioned on GitHubpytorchMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
tensorflow/models mentioned on GitHubtfSyntology: 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
toandaominh1997/EfficientDet.Pytorch mentioned on GitHubpytorchMITSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
wangermeng2021/EfficientDet-tensorflow2 mentioned on GitHubtfSyntology: not harvested report
wavce/efficientdet-tf2 mentioned on GitHubtfSyntology: not harvested report
xaviercanche/EfficientDet_V2 mentioned on GitHubpytorchSyntology: not harvested report
xuannianz/EfficientDet mentioned on GitHubtfApache-2.0Syntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified report
yangkunpeng-coder/EfficientDet_libtorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
zylo117/Yet-Another-EfficientDet-Pytorch mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
2023-MindSpore-1/ms-code-174 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-186 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-212 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code3 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large... (arXiv:2305.05773; that paper's own run record: 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); nothing checks that they implement this paper's method. report
Burf/tfdetection tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 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), Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
CuberrChen/efficientdet-paddle paddleSyntology: not harvested report
GuoQuanhao/EfficientDet-Paddle paddleMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
MindCode-4/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-MS-Code2/code0 mindsporeSyntology: not harvested report
MindSpore-MS-Code2/code0 mindsporeSyntology: not harvested report
MindSpore-MS-Code2/code0 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code8 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested 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
SweetyTian/efficientdet pytorchSyntology: not harvested report
code-implementation1/Code1 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
cuihu1998/EfficientDet-d0 mindsporeSyntology: not harvested report
gouthamvgk/coreml_conversion_hub pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
kentaroy47/efficientdet.pytorch pytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
lyqcom/efficientdet mindsporeApache-2.0Syntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

70 samples harvested: 55 ran (of which 1 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
4ran · our draft was wrong
3ran; the contract check could not run
44ran
15unverified

Licence: 7 of the 70 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 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”. “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.

google/automl official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
freeze_vars efficientdet/efficientdet_arch.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ceea6e679b6af5bc · report fixture: signature variables:list/1/Variable, pattern:str/0/str · returned list · level recorded 2026-09-22
Jintao-Huang/EfficientDet_PyTorch community (archive-listed) 10 samples, 6 ran (1 instrument-failed) · 4 unverified
cxcywh_to_ltrb models/utils.py ran fingerprinted Apache-2.0 (permissive) · 60dce678f58929c7 · report fixture: signature boxes:Tensor/2/float, as_tuple:bool/0/bool · returned Tensor · level recorded 2026-09-24
drop_connect in 73 papers
census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
models/efficientnet.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 53d13d88994382df · report fixture: signature x:Tensor/4/float, drop_p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
encode_boxes models/utils.py ran fingerprinted Apache-2.0 (permissive) · 08a96253f661fedd · report fixture: signature boxes:Tensor/2/float, anchors:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_same_padding in 16 papers models/efficientnet.py ran · honoured contract Apache-2.0 (permissive) · ce78adffe6b7cfbf · report fixture: signature in_size:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned tuple · level recorded 2026-09-22
ltrb_to_cxcywh models/utils.py ran fingerprinted Apache-2.0 (permissive) · 16b53a145d567a1a · report fixture: signature boxes:Tensor/2/float, as_tuple:bool/0/bool · returned Tensor · level recorded 2026-09-24
weighted_binary_focal_loss models/loss.py ran Apache-2.0 (permissive) · f93cdbff3f79254b · report fixture: signature pred:Tensor/1/float, target:Tensor/1/float, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-24
efficientdet_d0 models/efficientdet.py unverified Apache-2.0 (permissive) · 6dd16596102bce65 · report
efficientdet_d1 models/efficientdet.py unverified Apache-2.0 (permissive) · babb57bb2ec8e199 · report
efficientdet_d2 models/efficientdet.py unverified Apache-2.0 (permissive) · 22e07150104ea668 · report
ManfredGonzalez/multispectral-pineapple-detection community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 4 of 11, arg 1: rank 2, kind float, dtype float64
pre-processing/homography_align_SIFT.py ran · honoured contract fingerprinted no licence file found · pointer only · 34900df21ccd3b4f · report fixture: signature x:ndarray/2/float, lower:int/0/int, upper:int/0/int · returned ndarray · level recorded 2026-09-22
SharifElfouly/easy-model-zoo community (archive-listed) 10 samples, 9 ran (1 instrument-failed) · 1 unverified
BatchNorm2d in 9 papers easy_model_zoo/bisenet/bisenet.py ran MIT (permissive) · d3697beae5965412 · report fixture: signature out_chan:int/0/int · returned BatchNorm2d · level recorded 2026-09-24
aspectaware_resize_padding easy_model_zoo/efficientdet/efficientdetmodel.py ran MIT (permissive) · adbb9cd9ba4e566a · report fixture: signature image:ndarray/3/float, width:int/0/int, height:int/0/int, interpolation:int/0/int, means:ndarray/1/float · returned tuple · level recorded 2026-09-24
calc_iou in 17 papers easy_model_zoo/efficientdet/efficientdet/loss.py ran fingerprinted MIT (permissive) · 9b3d320614140152 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-24
collater easy_model_zoo/efficientdet/efficientdet/dataset.py ran MIT (permissive) · 089b0c6b3e840e5f · report fixture: signature data:list/1/dict · returned dict · level recorded 2026-09-24
construct_backbone in 6 papers easy_model_zoo/yolact/backbone.py ran MIT (permissive) · 87523070b15ff05c · report fixture: signature cfg:BackboneConfig/0/? · returned SimpleBackbone · level recorded 2026-09-25
conv3x3 in 1,376 papers easy_model_zoo/bisenet/bisenet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
create_layer_basic in 19 papers easy_model_zoo/bisenet/bisenet.py ran MIT (permissive) · c968417c62505b67 · report fixture: signature in_chan:int/0/int, out_chan:int/0/int, bnum:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-24
get_color_pallete easy_model_zoo/bisenet/vis.py ran MIT (permissive) · f218af101f9b0acd · report fixture: signature npimg:ndarray/2/int, dataset:str/0/str · returned Image · level recorded 2026-09-24
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
easy_model_zoo/efficientdet/efficientdetmodel.py ran MIT (permissive) · 78a46cad2c35f09d · report fixture: signature ori_imgs:list/1/ndarray, max_size:int/0/int, mean:tuple/1/float, std:tuple/1/float · returned tuple · level recorded 2026-09-24
darknetconvlayer easy_model_zoo/yolact/backbone.py unverified MIT (permissive) · 901e174e8a74774c · report
lvweiwolf/efficientdet community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
freeze_vars efficientdet_arch.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3af301f87fe2c911 · report fixture: signature variables:list/1/VariableWithName, pattern:str/0/str · returned list · level recorded 2026-09-22
sevakon/efficientdet community (archive-listed) 5 samples, 4 ran (1 instrument-failed) · 1 unverified
clip_boxes_ utils/anchors.py ran fingerprinted MIT (permissive) · fd3c92ef91740dc0 · report fixture: signature boxes:Tensor/2/float, size:Tensor/1/float · returned Tensor · level recorded 2026-09-24
decode_box_outputs utils/anchors.py ran MIT (permissive) · 219e3c611cd54c68 · report fixture: signature rel_codes:Tensor/3/float, anchors:Tensor/3/float · returned Tensor · level recorded 2026-09-24
drop_connect in 73 papers
census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
model/efficientnet/utils.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 2dd5dfa94542911e · report fixture: signature inputs:Tensor/4/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
encode_boxes_to_anchors utils/anchors.py ran fingerprinted MIT (permissive) · c605a8151aab62c5 · report fixture: signature boxes:Tensor/2/float, anchors:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24
collater dataloader.py unverified MIT (permissive) · d87e7e82b72f38f3 · report
shivam-raj/detector community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
remove_variables efficientdet_arch.py ran · our draft was wrong no licence file found · pointer only · 4982146c641543d1 · report fixture: signature variables:list/1/Variable, resnet_depth:int/0/int · returned list · level recorded 2026-09-22
signatrix/efficientdet community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
calc_iou in 17 papers src/loss.py ran fingerprinted MIT (permissive) · f4a9f170c94dd553 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_shape src/utils.py ran MIT (permissive) · ba85bbf2855c2ff4 · report fixture: signature image_shape:tuple/1/int, pyramid_levels:list/1/int · returned list · level recorded 2026-09-24
generate_anchors in 19 papers src/utils.py ran MIT (permissive) · 5b3a9cef8ec8c746 · report fixture: signature base_size:int/0/int, ratios:ndarray/1/float, scales:ndarray/1/float · returned ndarray · level recorded 2026-09-24
nms in 65 papers src/model.py ran MIT (permissive) · f35355d03c1b823d · report fixture: signature dets:Tensor/2/float, thresh:float/0/float · returned Tensor · level recorded 2026-09-24
shift in 22 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
src/utils.py ran MIT (permissive) · 7abc112d283442c7 · report fixture: signature shape:tuple/1/int, stride:int/0/int, anchors:ndarray/2/float · returned ndarray · level recorded 2026-09-24
collater src/dataset.py unverified MIT (permissive) · 07db8d49de7cb1cf · report
toandaominh1997/EfficientDet.Pytorch community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
anchors_for_shape models/module.py ran MIT (permissive) · 940d81699138177c · report fixture: signature image_shape:tuple/1/int, pyramid_levels:list/1/int, ratios:ndarray/1/float, scales:ndarray/1/float, strides:ndarray/1/int, sizes:ndarray/1/int, shapes_callback:NoneType/0/? · returned ndarray · level recorded 2026-09-24
compute_shape models/module.py ran MIT (permissive) · 1ef84ea5e6566d69 · report fixture: signature image_shape:tuple/1/int, pyramid_levels:list/1/int · returned list · level recorded 2026-09-24
detection_collate datasets/augmentation.py ran MIT (permissive) · 91497d83c3b331c3 · report fixture: signature batch:list/1/dict · returned tuple · level recorded 2026-09-24
generate_anchors in 19 papers models/module.py ran MIT (permissive) · 1279986e0f62b111 · report fixture: signature base_size:int/0/int, ratios:ndarray/1/float, scales:ndarray/1/float · returned ndarray · level recorded 2026-09-25
visualize in 13 papers datasets/visual_aug.py ran MIT (permissive) · 43fbbcaf0aa13b99 · report fixture: signature annotations:dict/0/?, category_id_to_name:dict/0/? · returned ndarray · level recorded 2026-09-24
visualize_bbox datasets/visual_aug.py ran MIT (permissive) · 206ff4c637a23abe · report fixture: signature img:ndarray/3/int, bbox:tuple/1/int, class_id:int/0/int, class_idx_to_name:dict/0/?, color:tuple/1/int, thickness:int/0/int · returned ndarray · level recorded 2026-09-24
collater datasets/augmentation.py unverified MIT (permissive) · f82f955d16ba9998 · report
multi_apply in 11 papers models/retinahead.py unverified MIT (permissive) · 8f464b0fc5da3347 · report
xuannianz/EfficientDet community (archive-listed) 11 samples, 8 ran (0 instrument-failed) · 3 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
model.py ran Apache-2.0 (permissive) · a357296d5e1f5ba3 · report fixture: signature num_channels:int/0/int, kernel_size:int/0/int, strides:int/0/int, name:str/0/str, freeze_bn:bool/0/bool · returned function · level recorded 2026-09-24
bbox_transform_inv in 11 papers layers.py ran Apache-2.0 (permissive) · 8a24d71a96af0391 · report fixture: signature boxes:EagerTensor/2/float, deltas:EagerTensor/2/float, scale_factors:list/1/float · returned SymbolicTensor · level recorded 2026-09-24
filter_detections layers.py ran Apache-2.0 (permissive) · 90d221581bcaf7c7 · report fixture: signature boxes:EagerTensor/2/float, classification:EagerTensor/2/float, alphas:EagerTensor/2/float, ratios:EagerTensor/1/float, class_specific_filter:bool/0/bool, nms:bool/0/bool, score_threshold:float/0/float, max_detections:int/0/int, nms_threshold:float/0/float, detect_quadrangle:bool/0/bool · returned list · level recorded 2026-09-24
focal losses.py ran Apache-2.0 (permissive) · c1389040930b96b7 · report fixture: signature alpha:float/0/float, gamma:float/0/float · returned function · level recorded 2026-09-24
round_filters in 47 papers efficientnet.py ran Apache-2.0 (permissive) · 00c946065068bd77 · report fixture: signature filters:int/0/int, width_coefficient:float/0/float, depth_divisor:int/0/int · returned int · level recorded 2026-09-24
round_repeats in 39 papers efficientnet.py ran fingerprinted Apache-2.0 (permissive) · 6cc796a8212b5586 · report fixture: signature repeats:int/0/int, depth_coefficient:float/0/float · returned int · level recorded 2026-09-25
smooth_l1 in 7 papers losses.py ran Apache-2.0 (permissive) · eb88cc992d53c796 · report fixture: signature sigma:float/0/float · returned function · level recorded 2026-09-24
smooth_l1_quad losses.py ran Apache-2.0 (permissive) · 36844f48b65fa098 · report fixture: signature sigma:float/0/float · returned function · level recorded 2026-09-24
SeparableConvBlock model.py unverified Apache-2.0 (permissive) · 4b223f0c5774a3a3 · report
freeze_session freeze_model.py unverified Apache-2.0 (permissive) · 47bdd5f22feb61e7 · report
get_frozen_graph inference_frozen_graph.py unverified Apache-2.0 (permissive) · 927fdf776b68d29e · report
GuoQuanhao/EfficientDet-Paddle community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
batched_nms in 29 papers utils/batch_nms.py ran MIT (permissive) · 50373489e7c21793 · report fixture: signature boxes:ndarray/2/float, scores:ndarray/1/float, idxs:ndarray/1/int, iou_threshold:float/0/float · returned list · level recorded 2026-09-24
collater efficientdet/dataset.py ran MIT (permissive) · 1a2f8db3b80e6f37 · report fixture: signature data:list/1/dict · returned dict · level recorded 2026-09-24
nms in 65 papers utils/batch_nms.py ran MIT (permissive) · 35cb2fd811f8eb66 · report fixture: signature dets:ndarray/2/float, scores:ndarray/1/float, thresh:float/0/float · returned list · level recorded 2026-09-24
round_filters in 47 papers efficientnet/utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 826e2e91d6a9ec09 · report fixture: signature filters:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22
round_repeats in 39 papers efficientnet/utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 4d8e794b593d34a0 · report fixture: signature repeats:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22
display efficientdet_test_videos.py unverified MIT (permissive) · f1c6eabae899cbc7 · report
kentaroy47/efficientdet.pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
make_loc_conf utils/efficientdet.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · d93c6090474e0d1a · report fixture: signature num_classes:int/0/int, bbox_aspect_num:list/1/int · returned tuple · level recorded 2026-09-22
lyqcom/efficientdet community (archive-listed) 9 samples, 7 ran (0 instrument-failed) · 2 unverified
batched_nms in 29 papers src/nms.py ran Apache-2.0 (permissive) · f7f08e847945b8ea · report fixture: signature boxes:ndarray/2/float, scores:ndarray/1/float, idxs:ndarray/1/int, iou_threshold:float/0/float · returned ndarray · level recorded 2026-09-24
clipBoxes src/utils.py ran Apache-2.0 (permissive) · b1f5f075b76392b9 · report fixture: signature boxes:ndarray/3/float, img:ndarray/4/float · returned ndarray · level recorded 2026-09-24
get_lr_cosine src/lr_schedule.py ran Apache-2.0 (permissive) · cad8943a75251ca7 · report fixture: signature init_lr:float/0/float, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, t_max:int/0/int, eta_min:float/0/float · returned ndarray · level recorded 2026-09-24
get_lr_exponential src/lr_schedule.py ran Apache-2.0 (permissive) · edf1fc6be4a7628c · report fixture: signature init_lr:float/0/float, lr_epochs:list/1/int, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, lr_gamma:float/0/float · returned ndarray · level recorded 2026-09-24
linear_warmup_lr in 10 papers src/lr_schedule.py ran fingerprinted Apache-2.0 (permissive) · 56d39004d57cb3a2 · report fixture: signature current_step:int/0/int, warmup_steps:int/0/int, base_lr:float/0/float, init_lr:float/0/float · returned float · level recorded 2026-09-24
name_map src/convert_weight.py ran Apache-2.0 (permissive) · 88acb93cc8aa1c27 · report fixture: signature ckpt:dict/0/? · returned dict · level recorded 2026-09-24
nms in 65 papers src/nms.py ran Apache-2.0 (permissive) · 12e01fa98323c582 · report fixture: signature all_boxes:ndarray/2/float, all_scores:ndarray/1/float, thres:float/0/float · returned ndarray · level recorded 2026-09-24
bbox_transform in 11 papers src/utils.py unverified Apache-2.0 (permissive) · 80ef81417a6a01c0 · report
load_model in 479 papers src/convert_weight.py unverified Apache-2.0 (permissive) · 6b0e7aeddc8d13b6 · report

Tasks

AutoMLObjectObject DetectionReal-Time Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival EfficientDet-D7 (1536) box AP 52.1 #68 of 220 Archive leaderboard report
Object Detection COCO minival EfficientDet-D7x (single-scale) AP50 73.4 #214 of 220 Archive leaderboard report
Object Detection COCO minival EfficientDet-D7x (single-scale) AP75 59.0 #214 of 220 Archive leaderboard report
Object Detection COCO minival EfficientDet-D7x (single-scale) APL 67.9 #214 of 220 Archive leaderboard report
Object Detection COCO minival EfficientDet-D7x (single-scale) APM 58.0 #214 of 220 Archive leaderboard report
Object Detection COCO minival EfficientDet-D7x (single-scale) APS 40.0 #214 of 220 Archive leaderboard report
Object Detection COCO test-dev EfficientDet-D7 (1536) AP50 71.6 #69 of 225 Archive leaderboard report
Object Detection COCO test-dev EfficientDet-D7 (1536) AP75 56.9 #69 of 225 Archive leaderboard report
Object Detection COCO test-dev EfficientDet-D7 (1536) box mAP 52.6 #69 of 225 Archive leaderboard report
Object Detection COCO-O EfficientDet-D5 (EfficientNet-B5) Average mAP 28.5 #22 of 45 Archive leaderboard report
Object Detection COCO-O EfficientDet-D5 (EfficientNet-B5) Effective Robustness 5.44 #22 of 45 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

Introduced by this paper: BiFPN, EfficientDet

1x1 ConvolutionAverage PoolingBatch NormalizationBiFPNConvolutionCosine AnnealingDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientDetEfficientNetFocal LossImage Scale AugmentationInverted Residual BlockLinear Warmup With Cosine AnnealingPointwise ConvolutionRMSPropRandom Horizontal FlipReLUSGD with MomentumSigmoid ActivationSqueeze-and-Excitation BlockWeight Decay

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