Papers › Finding Tiny Faces

Finding Tiny Faces

13 Dec 2016CVPR 2017 7arXiv:1612.04402archive 2025-07-28

Peiyun Hu, Deva Ramanan

Though tremendous strides have been made in object recognition, one of the remaining open challenges is detecting small objects. We explore three aspects of the problem in the context of finding small faces: the role of scale invariance, image resolution, and contextual reasoning. While most recognition approaches aim to be scale-invariant, the cues for recognizing a 3px tall face are fundamentally different than those for recognizing a 300px tall face. We take a different approach and train separate detectors for different scales. To maintain efficiency, detectors are trained in a multi-task fashion: they make use of features extracted from multiple layers of single (deep) feature hierarchy. While training detectors for large objects is straightforward, the crucial challenge remains training detectors for small objects. We show that context is crucial, and define templates that make use of massively-large receptive fields (where 99% of the template extends beyond the object of interest). Finally, we explore the role of scale in pre-trained deep networks, providing ways to extrapolate networks tuned for limited scales to rather extreme ranges. We demonstrate state-of-the-art results on massively-benchmarked face datasets (FDDB and WIDER FACE). In particular, when compared to prior art on WIDER FACE, our results reduce error by a factor of 2 (our models produce an AP of 82% while prior art ranges from 29-64%).

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 14 code samples harvested from 4 repositories linked to this paper: 8 ran (of which 0 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) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 14 samples from 4 repositories, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

Eltomad/Tiny_Faces mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Jagannathrk2020/Face-detection-and-counting- mentioned on GitHubtfSyntology: not harvested report
Speacer/Super-Resolution-Generative-Adversarial-Networks mentioned on GitHubtfMITSyntology: not harvested report
alexattia/ExtendedTinyFaces mentioned on GitHubtfSyntology: not harvested report
atom06/Tiny_Faces_in_Tensorflow_v2 mentioned on GitHubtfMITSyntology: not harvested report
carlosb1/upc-aidl-19-team4 mentioned on GitHubpytorchSyntology: not harvested report
chinakook/hr101_mxnet mentioned on GitHubtfMITSyntology: not harvested report
clxiao/Tiny_Faces_in_Tensorflow mentioned on GitHubtfMITSyntology: not harvested report
cydonia999/Tiny_Faces_in_Tensorflow mentioned on GitHubtfMITSyntology: not harvested report
gpspelle/Crowd-Counting mentioned on GitHubMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
iitmcvg/Demo-of-face-detection-and-counting- mentioned on GitHubtfSyntology: not harvested report
krantirk/Face-detection-and-counting- mentioned on GitHubtfSyntology: not harvested report
mrw-soumik/Tiny-Faces-in-Tensorflow mentioned on GitHubtfSyntology: not harvested report
neuralet/facemask mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
peiyunh/tiny mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
shahidul56/Tiny_Faces_in_Tensorflow_msc mentioned on GitHubtfMITSyntology: not harvested report
tmdgus1237/HelloWorld2018-2 mentioned on GitHubNOASSERTIONSyntology: not harvested report
tuyentv2009/Face-Recognition- mentioned on GitHubtfSyntology: not harvested report
varununleashed/tiny_faces_temp mentioned on GitHubtfMITSyntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
GuoQuanhao/Tiny-Face-Paddle paddleMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report

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

Code Syntology ran Syntology

14 samples harvested: 8 ran (of which 0 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) · 6 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.

8ran
6unverified

Licence: 1 of the 14 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 4 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.

Eltomad/Tiny_Faces community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
nms in 65 papers util.py ran fingerprinted MIT (permissive) · d6a73bba4327bf04 · report fixture: signature dets:ndarray/2/float, prob_thresh:float/0/float · returned list · level recorded 2026-09-26
gpspelle/Crowd-Counting community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
calc_area inside.py ran MIT (permissive) · f848974ea09f6c76 · report fixture: signature Ax:float/0/float, Ay:float/0/float, Bx:float/0/float, By:float/0/float, Cx:float/0/float, Cy:float/0/float · returned float64 · level recorded 2026-09-26
get_image in 52 papers find_people.py ran MIT (permissive) · 6126b300e57ac811 · report fixture: signature im_path:str/0/str · returned ndarray · level recorded 2026-09-26
maaae keras_train.py unverified MIT (permissive) · 2e372208416e2c16 · report
mssse keras_train.py unverified MIT (permissive) · fd023123fe830ac0 · report
varununleashed/tiny_faces_temp community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
Average in 8 papers tiny_face_regions_of_interest.py ran fingerprinted MIT (permissive) · 905d2ecd38193e5d · report fixture: signature lst:list/1/int · returned int · level recorded 2026-09-26
box_size_calculate tiny_face_regions_of_interest.py ran fingerprinted MIT (permissive) · 280de894d1161d94 · report fixture: signature r:list/1/int · returned tuple · level recorded 2026-09-26
crop_faces_save tiny_face_regions_of_interest.py unverified MIT (permissive) · 08e89c9ecd0e1150 · report
download in 53 papers download_WIDERFACE.py unverified MIT (permissive) · c1c3c4d881e7b0ae · report
get_confirm_token in 41 papers download_WIDERFACE.py unverified MIT (permissive) here; the stored copy is pointer only · 135b3dc835ffe6ad · report
GuoQuanhao/Tiny-Face-Paddle community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
balance_sampling models/utils.py ran MIT (permissive) · 249c084ce92ceb64 · report fixture: signature label_cls:ndarray/2/int, pos_fraction:float/0/float, sample_size:int/0/int · returned ndarray · level recorded 2026-09-26
calculate_gain in 14 papers models/initializer.py ran MIT (permissive) · d32692be0e110bc9 · report fixture: signature nonlinearity:str/0/str, param:NoneType/0/? · returned float · level recorded 2026-09-26
regression_refinement models/utils.py ran MIT (permissive) · 20e5dfe30b779157 · report fixture: signature tx:ndarray/1/float, ty:ndarray/1/float, tw:ndarray/1/float, th:ndarray/1/float, cx:ndarray/1/float, cy:ndarray/1/float, cw:ndarray/1/float, ch:ndarray/1/float, indices:ndarray/1/int · returned ndarray · level recorded 2026-09-26
get_bboxes models/utils.py unverified MIT (permissive) · 504c00b3ebee7453 · report

Tasks

Face DetectionObject Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Detection WIDER Face (Hard) Massively-large receptive fields AP 0.823 #27 of 40 Archive leaderboard report
Face Detection WIDER Face (Medium) Massively-large receptive fields AP 0.908 #24 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.

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