Papers › Sample and Computation Redistribution for Efficient Face Detection

Sample and Computation Redistribution for Efficient Face Detection

10 May 2021ICLR 2022 4arXiv:2105.04714archive 2025-07-28

Jia Guo, Jiankang Deng, Alexandros Lattas, Stefanos Zafeiriou

Although tremendous strides have been made in uncontrolled face detection, efficient face detection with a low computation cost as well as high precision remains an open challenge. In this paper, we point out that training data sampling and computation distribution strategies are the keys to efficient and accurate face detection. Motivated by these observations, we introduce two simple but effective methods (1) Sample Redistribution (SR), which augments training samples for the most needed stages, based on the statistics of benchmark datasets; and (2) Computation Redistribution (CR), which reallocates the computation between the backbone, neck and head of the model, based on a meticulously defined search methodology. Extensive experiments conducted on WIDER FACE demonstrate the state-of-the-art efficiency-accuracy trade-off for the proposed \scrfd family across a wide range of compute regimes. In particular, \scrfdf{34} outperforms the best competitor, TinaFace, by 3.86% (AP at hard set) while being more than 3× faster on GPUs with VGA-resolution images. We also release our code to facilitate future research.

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

No sample from the archive's official repository (deepinsight/insightface) is linked to this paper; the 7 samples below come from 1 community repository. Syntology harvested code from deepinsight/insightface for another paper.

deepinsight/insightface: Syntology's graph links these samples to A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data (arXiv:2601.07576; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method.

Syntology 7 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 7 samples from 1 repository, 7 ran (6 with no instrument failure; 1 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.

deepinsight/insightface officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data (arXiv:2601.07576; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
aralhekimoglu/face mentioned on GitHubpytorchMITSyntology: 7 samples, 7 ran (1 instrument-failed) · 0 unverified report
bovifocr/insightface mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition... (arXiv:2203.15565; that paper's own run record: 10 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
pedrobvidal/insightface mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition... (arXiv:2203.15565; that paper's own run record: 10 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
yakhyo/gaze-estimation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified) and L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments (arXiv:2203.03339; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
yakhyo/head-pose-estimation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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), Fine-Grained Head Pose Estimation Without Keypoints (arXiv:1710.00925; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified) and MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/-insightface mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition... (arXiv:2203.15565; that paper's own run record: 10 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
yakhyo/retinaface-pytorch pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified), MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified) and RetinaFace: Single-stage Dense Face Localisation in the Wild (arXiv:1905.00641; that paper's own run record: 73 ran (of which 0 constructed an object rather than computing a result; 58 with no instrument failure: 1 honoured, 4 violated, 53 with no contract checked; 15 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
1ran; the contract check could not run
4ran

Licence: 2 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 aralhekimoglu/face. “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.

aralhekimoglu/face community (archive-listed) 7 samples, 7 ran (1 instrument-failed) · 0 unverified
calculate_accuracy in 65 papers recognition/oneflow_face/validation_util.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · f975336b5d5f1a80 · report fixture: signature threshold:float/0/float, dist:ndarray/1/float, actual_issame:ndarray/1/bool · returned tuple · level recorded 2026-09-22
calculate_roc in 14 papers recognition/oneflow_face/validation_util.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) here; the stored copy is pointer only · 5f529c4af000c070 · report fixture: signature thresholds:ndarray/1/float, embeddings1:ndarray/2/float, embeddings2:ndarray/2/float, actual_issame:ndarray/1/bool, nrof_folds:int/0/int, pca:int/0/int · returned tuple · level recorded 2026-09-22
distance in 53 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
recognition/oneflow_face/validation_util.py ran fingerprinted MIT (permissive) · 7522ada649e29d57 · report fixture: signature embeddings1:ndarray/2/float, embeddings2:ndarray/2/float, distance_metric:int/0/int · returned ndarray · level recorded 2026-09-24
flip_data recognition/oneflow_face/insightface_val.py ran fingerprinted MIT (permissive) · 5b7430811591e445 · report fixture: signature images:ndarray/4/int · returned ndarray · level recorded 2026-09-24
square_crop python-package/insightface/utils/face_align.py ran MIT (permissive) · b453cc5fbf797449 · report fixture: signature im:ndarray/3/int, S:int/0/int · returned tuple · level recorded 2026-09-24
str2bool in 533 papers recognition/oneflow_face/insightface_train.py ran · violated contract MIT (permissive) · a957019ca36a6747 · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
str2list in 12 papers recognition/oneflow_face/insightface_train.py ran MIT (permissive) · 326b29422fdffda6 · report fixture: signature x:str/0/str · returned list · level recorded 2026-09-24

Tasks

Face Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Detection WIDER Face (Easy) SCRFD-34GF AP 0.9606 #8 of 27 Archive leaderboard report
Face Detection WIDER Face (Easy) SCRFD-10GF AP 0.9516 #14 of 27 Archive leaderboard report
Face Detection WIDER Face (Easy) SCRFD-2.5GF AP 0.9378 #20 of 27 Archive leaderboard report
Face Detection WIDER Face (Easy) SCRFD-0.5GF AP 0.9057 #23 of 27 Archive leaderboard report
Face Detection WIDER Face (Hard) SCRFD-34GF AP 0.8529 #19 of 40 Archive leaderboard report
Face Detection WIDER Face (Hard) SCRFD-10GF AP 0.8305 #25 of 40 Archive leaderboard report
Face Detection WIDER Face (Hard) SCRFD-2.5GF AP 0.7787 #29 of 40 Archive leaderboard report
Face Detection WIDER Face (Hard) SCRFD-0.5GF AP 0.6851 #32 of 40 Archive leaderboard report
Face Detection WIDER Face (Medium) SCRFD-34GF AP 0.9492 #7 of 37 Archive leaderboard report
Face Detection WIDER Face (Medium) SCRFD-10GF AP 0.9387 #16 of 37 Archive leaderboard report
Face Detection WIDER Face (Medium) SCRFD-2.5GF AP 0.9216 #22 of 37 Archive leaderboard report
Face Detection WIDER Face (Medium) SCRFD-0.5GF AP 0.8812 #28 of 37 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

Computation RedistributionSample RedistributionTinaFace

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