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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1612.04402")

Code

Syntology Ran 0 of 14 code samples harvested from 4 repositories linked to this paper; 14 have no recorded run.

By repository: community (archive-listed): 14 samples from 4 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

Eltomad/Tiny_Faces mentioned on GitHubtfMIT report
alexattia/ExtendedTinyFaces mentioned on GitHubtf report
atom06/Tiny_Faces_in_Tensorflow_v2 mentioned on GitHubtfMIT report
carlosb1/upc-aidl-19-team4 mentioned on GitHubpytorch report
chinakook/hr101_mxnet mentioned on GitHubtfMIT report
clxiao/Tiny_Faces_in_Tensorflow mentioned on GitHubtfMIT report
cydonia999/Tiny_Faces_in_Tensorflow mentioned on GitHubtfMIT report
gpspelle/Crowd-Counting mentioned on GitHubMIT report
neuralet/facemask mentioned on GitHubtfNOASSERTION report
peiyunh/tiny mentioned on GitHubpytorchNOASSERTION report
tmdgus1237/HelloWorld2018-2 mentioned on GitHubNOASSERTION report
tuyentv2009/Face-Recognition- mentioned on GitHubtf report
varununleashed/tiny_faces_temp mentioned on GitHubtfMIT 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; 0 ran; 0 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

14unverified

Licence: 0 of the 14 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Average varununleashed/tiny_faces_temp/tiny_face_regions_of_interest.py community (archive-listed) unverified MIT (permissive) · 905d2ecd38193e5d · report
balance_sampling GuoQuanhao/Tiny-Face-Paddle/models/utils.py community (archive-listed) unverified MIT (permissive) · 249c084ce92ceb64 · report
box_size_calculate varununleashed/tiny_faces_temp/tiny_face_regions_of_interest.py community (archive-listed) unverified MIT (permissive) · 280de894d1161d94 · report
calc_area gpspelle/Crowd-Counting/inside.py community (archive-listed) unverified MIT (permissive) · f848974ea09f6c76 · report
calculate_gain GuoQuanhao/Tiny-Face-Paddle/models/initializer.py community (archive-listed) unverified MIT (permissive) · d32692be0e110bc9 · report
crop_faces_save varununleashed/tiny_faces_temp/tiny_face_regions_of_interest.py community (archive-listed) unverified MIT (permissive) · 08e89c9ecd0e1150 · report
download varununleashed/tiny_faces_temp/download_WIDERFACE.py community (archive-listed) unverified MIT (permissive) · c1c3c4d881e7b0ae · report
get_bboxes GuoQuanhao/Tiny-Face-Paddle/models/utils.py community (archive-listed) unverified MIT (permissive) · 504c00b3ebee7453 · report
get_confirm_token varununleashed/tiny_faces_temp/download_WIDERFACE.py community (archive-listed) unverified MIT (permissive) · 135b3dc835ffe6ad · report
get_image gpspelle/Crowd-Counting/find_people.py community (archive-listed) unverified MIT (permissive) · 6126b300e57ac811 · report
maaae gpspelle/Crowd-Counting/keras_train.py community (archive-listed) unverified MIT (permissive) · 2e372208416e2c16 · report
mssse gpspelle/Crowd-Counting/keras_train.py community (archive-listed) unverified MIT (permissive) · fd023123fe830ac0 · report
nms Eltomad/Tiny_Faces/util.py community (archive-listed) unverified MIT (permissive) · d6a73bba4327bf04 · report
regression_refinement GuoQuanhao/Tiny-Face-Paddle/models/utils.py community (archive-listed) unverified MIT (permissive) · 20e5dfe30b779157 · 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