Papers › SeesawFaceNets: sparse and robust face verification model for mobile platform

SeesawFaceNets: sparse and robust face verification model for mobile platform

24 Aug 2019arXiv 2019 8arXiv:1908.09124archive 2025-07-28

Jintao Zhang

Deep Convolutional Neural Network (DCNNs) come to be the most widely used solution for most computer vision related tasks, and one of the most important application scenes is face verification. Due to its high-accuracy performance, deep face verification models of which the inference stage occurs on cloud platform through internet plays the key role on most prectical scenes. However, two critical issues exist: First, individual privacy may not be well protected since they have to upload their personal photo and other private information to the online cloud backend. Secondly, either training or inference stage is time-comsuming and the latency may affect customer experience, especially when the internet link speed is not so stable or in remote areas where mobile reception is not so good, but also in cities where building and other construction may block mobile signals. Therefore, designing lightweight networks with low memory requirement and computational cost is one of the most practical solutions for face verification on mobile platform. In this paper, a novel mobile network named SeesawFaceNets, a simple but effective model, is proposed for productively deploying face recognition for mobile devices. Dense experimental results have shown that our proposed model SeesawFaceNets outperforms the baseline MobilefaceNets, with only 66%(146M VS 221M MAdds) computational cost, smaller batch size and less training steps, and SeesawFaceNets achieve comparable performance with other SOTA model e.g. mobiface with only 54.2%(1.3M VS 2.4M) parameters and 31.6%(146M VS 462M MAdds) computational cost, It is also eventually competitive against large-scale deep-networks face recognition on all 5 listed public validation datasets, with 6.5%(4.2M VS 65M) parameters and 4.35%(526M VS 12G MAdds) computational cost.

PaperPDFCodeCode 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 17 code samples harvested from 3 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 17 samples from 3 repositories, 15 ran (10 with no instrument failure; 5 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 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.

cvtower/SeesawNet-pytorch-reimplement mentioned on GitHubpytorchSyntology: not harvested report
cvtower/SeesawNet_pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
cvtower/seesawfacenet_pytorch mentioned on GitHubpytorchMITSyntology: 12 samples, 10 ran (1 instrument-failed) · 2 unverified report
didi/AoE mentioned on GitHubtfnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
pshashk/seesaw-facenet mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 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

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
1ran; the contract check could not run
8ran
2unverified

Licence: 5 of the 17 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 3 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.

cvtower/SeesawNet_pytorch community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
conv_1x1_bn in 59 papers code/models/imagenet/seesaw.py ran · our draft was wrong no licence file found · pointer only · 0db9f814cdec6488 · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_bn in 88 papers code/models/imagenet/seesaw.py ran · our draft was wrong no licence file found · pointer only · 80d427a5f4557b3d · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
cvtower/seesawfacenet_pytorch community (archive-listed) 12 samples, 10 ran (1 instrument-failed) · 2 unverified
calibrate_box src/mtcnn_pytorch/src/box_utils.py ran fingerprinted MIT (permissive) · 6b0e6100d2ca104e · report fixture: signature bboxes:ndarray/2/float, offsets:ndarray/2/float · returned ndarray · level recorded 2026-09-24
convert_to_square src/mtcnn_pytorch/src/box_utils.py ran fingerprinted MIT (permissive) · c4e1ca09fcca76fc · report fixture: signature bboxes:ndarray/2/float · returned ndarray · level recorded 2026-09-24
findNonreflectiveSimilarity in 5 papers src/mtcnn_pytorch/src/matlab_cp2tform.py ran MIT (permissive) · d074710facc3ca20 · report fixture: signature uv:ndarray/2/float, xy:ndarray/2/float, options:dict/0/? · returned tuple · level recorded 2026-09-24
get_affine_transform_matrix in 5 papers src/mtcnn_pytorch/src/align_trans.py ran · honoured contract fingerprinted MIT (permissive) · b7f364dbce963974 · report fixture: signature src_pts:ndarray/2/float, dst_pts:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_config in 203 papers src/config.py ran MIT (permissive) · 7068d53e5a1d27e7 · report fixture: signature training:bool/0/bool · returned EasyDict · level recorded 2026-09-24
get_reference_facial_points in 5 papers src/mtcnn_pytorch/src/align_trans.py ran MIT (permissive) · a88ec2b4b2ac122c · report fixture: signature output_size:tuple/1/int, inner_padding_factor:float/0/float, outer_padding:tuple/1/int, default_square:bool/0/bool · returned ndarray · level recorded 2026-09-24
nms in 65 papers src/mtcnn_pytorch/src/box_utils.py ran MIT (permissive) · 522ee6c31c17d845 · report fixture: signature boxes:ndarray/2/float, overlap_threshold:float/0/float, mode:str/0/str · returned list · level recorded 2026-09-24
show_bboxes src/mtcnn_pytorch/src/visualization_utils.py ran MIT (permissive) · 1a075d92bb280328 · report fixture: signature img:Image/0/?, bounding_boxes:ndarray/2/float, facial_landmarks:ndarray/2/float · returned Image · level recorded 2026-09-24
tformfwd in 5 papers src/mtcnn_pytorch/src/matlab_cp2tform.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · b4e2f92e3ce5abc6 · report fixture: signature trans:ndarray/2/float, uv:ndarray/2/float · returned ndarray · level recorded 2026-09-24
tforminv in 5 papers src/mtcnn_pytorch/src/matlab_cp2tform.py ran MIT (permissive) · 6661cdf22fccc11e · report fixture: signature trans:ndarray/2/float, uv:ndarray/2/float · returned ndarray · level recorded 2026-09-24
detect_faces src/mtcnn_pytorch/src/detector.py unverified MIT (permissive) · 15396a0e5161d1a2 · report
run_first_stage src/mtcnn_pytorch/src/first_stage.py unverified MIT (permissive) · c2027475131174ef · report
pshashk/seesaw-facenet community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
model.py ran · our draft was wrong no licence file found · pointer only · 41b5161a608d5f29 · report fixture: signature c_in:int/0/int, groups:int/0/int, c_out:int/0/int, stride:int/0/int, repeat:int/0/int · returned Residual · level recorded 2026-09-22
Conv in 30 papers
census: 8 implementations from 8 papers, 8 distinct outputs across 2 buckets, one shared input per bucket
model.py ran · our draft was wrong no licence file found · pointer only · b71052fb86154367 · report fixture: signature c_in:int/0/int, c_out:int/0/int, ks:int/0/int, stride:int/0/int, pad:bool/0/bool, dwise:bool/0/bool · returned ConvBn2d · level recorded 2026-09-22
hard_sigmoid in 15 papers model.py ran · honoured contract fingerprinted no licence file found · pointer only · 8b5594729a056dad · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22

Tasks

Face RecognitionFace VerificationLightweight Face Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lightweight Face Recognition AgeDB-30 Seesaw-shuffleFaceNet(mobi) Accuracy 0.9648 #2 of 5 Archive leaderboard report
Lightweight Face Recognition AgeDB-30 Seesaw-shuffleFaceNet(mobi) MParams 2.8 #2 of 5 Archive leaderboard report
Lightweight Face Recognition CFP-FP Seesaw-shuffleFaceNet(mobi) Accuracy 0.9307 #4 of 4 Archive leaderboard report
Lightweight Face Recognition CFP-FP Seesaw-shuffleFaceNet(mobi) MParams 2.8 #4 of 4 Archive leaderboard report
Lightweight Face Recognition LFW Seesaw-shuffleFaceNet(mobi) Accuracy 0.9965 #4 of 6 Archive leaderboard report
Lightweight Face Recognition LFW Seesaw-shuffleFaceNet(mobi) MParams 2.8 #4 of 6 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

SPEED

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