Papers › EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse

EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse

15 Jun 2019arXiv:1906.06579archive 2025-07-28

YoungJoon Yoo, Dongyoon Han, Sangdoo Yun

In this paper, we propose a new multi-scale face detector having an extremely tiny number of parameters (EXTD),less than 0.1 million, as well as achieving comparable performance to deep heavy detectors. While existing multi-scale face detectors extract feature maps with different scales from a single backbone network, our method generates the feature maps by iteratively reusing a shared lightweight and shallow backbone network. This iterative sharing of the backbone network significantly reduces the number of parameters, and also provides the abstract image semantics captured from the higher stage of the network layers to the lower-level feature map. The proposed idea is employed by various model architectures and evaluated by extensive experiments. From the experiments from WIDER FACE dataset, we show that the proposed face detector can handle faces with various scale and conditions, and achieved comparable performance to the more massive face detectors that few hundreds and tens times heavier in model size and floating point operations.

PaperPDFCodeCode 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="1906.06579")

Code

Syntology Ran 4 of 13 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 11 samples from 1 repository, 2 ran; community (archive-listed): 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

clovaai/EXTD_Pytorch officialmentioned on GitHubpytorchMIT report
SeungyounShin/EXTD mentioned on GitHubpytorch 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

13 samples harvested; 4 ran; 0 honoured the contract we drafted; 9 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.

2ran · our draft was wrong
2ran · fixture could not drive it
9unverified

Licence: 2 of the 13 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 2 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.

intersect clovaai/EXTD_Pytorch/layers/bbox_utils.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · f01c5f73515770a5 · report
point_form clovaai/EXTD_Pytorch/layers/bbox_utils.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 3bea1addc1e14162 · report
add_extras_mobileFace clovaai/EXTD_Pytorch/EXTD_32.py official repository unverified MIT (permissive) · f7dd0fc85b99dadd · report
center_size clovaai/EXTD_Pytorch/layers/bbox_utils.py official repository unverified MIT (permissive) · 1283157b9af10fce · report
conv_1x1_bn clovaai/EXTD_Pytorch/mobileFacenet_32_PReLU.py official repository unverified MIT (permissive) · 20c32d5668430dcd · report
conv_bn clovaai/EXTD_Pytorch/mobileFacenet_32_PReLU.py official repository unverified MIT (permissive) · 18aec87cea006da3 · report
get_gt_boxes clovaai/EXTD_Pytorch/eval_tools/evaluation.py official repository unverified MIT (permissive) · b8864cd681dd62de · report
get_gt_boxes_from_txt clovaai/EXTD_Pytorch/eval_tools/evaluation.py official repository unverified MIT (permissive) · fa5b759a22a26bb3 · report
parse_wider_file clovaai/EXTD_Pytorch/prepare_wider_data.py official repository unverified MIT (permissive) · 0feb7fb26b64b471 · report
read_pred_file clovaai/EXTD_Pytorch/eval_tools/evaluation.py official repository unverified MIT (permissive) · 524d5a85cd29ba7c · report
upsample clovaai/EXTD_Pytorch/EXTD_32.py official repository unverified MIT (permissive) · 40d252cf22e9e1ea · report
bbox_predictor SeungyounShin/EXTD/EXTD.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · f2e50f49c109c032 · report
class_predictor SeungyounShin/EXTD/EXTD.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · c112e1e0e8ec8d8c · report

Tasks

Face Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Detection WIDER Face (Hard) EXTD AP 0.850 #22 of 40 Archive leaderboard report
Face Detection WIDER Face (Medium) EXTD AP 0.903 #25 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