Papers › LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition

LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition

13 Mar 2024CVPR 2024 1arXiv:2403.08161archive 2025-07-28

Zhonglin Sun, Chen Feng, Ioannis Patras, Georgios Tzimiropoulos

In this work we focus on learning facial representations that can be adapted to train effective face recognition models, particularly in the absence of labels. Firstly, compared with existing labelled face datasets, a vastly larger magnitude of unlabeled faces exists in the real world. We explore the learning strategy of these unlabeled facial images through self-supervised pretraining to transfer generalized face recognition performance. Moreover, motivated by one recent finding, that is, the face saliency area is critical for face recognition, in contrast to utilizing random cropped blocks of images for constructing augmentations in pretraining, we utilize patches localized by extracted facial landmarks. This enables our method - namely LAndmark-based Facial Self-supervised learning LAFS), to learn key representation that is more critical for face recognition. We also incorporate two landmark-specific augmentations which introduce more diversity of landmark information to further regularize the learning. With learned landmark-based facial representations, we further adapt the representation for face recognition with regularization mitigating variations in landmark positions. Our method achieves significant improvement over the state-of-the-art on multiple face recognition benchmarks, especially on more challenging few-shot scenarios.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 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: official repository: 14 samples from 1 repository, 12 ran (10 with no instrument failure; 2 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.

szlbiubiubiu/lafs_cvpr2024 officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 12 ran (2 instrument-failed) · 2 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: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 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 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 · our draft was wrong
1ran; the contract check could not run
9ran
2unverified

Licence: 14 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 szlbiubiubiu/lafs_cvpr2024. “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.

szlbiubiubiu/lafs_cvpr2024 official repository 14 samples, 12 ran (2 instrument-failed) · 2 unverified
FeedForward in 198 papers face_pre_pro/ViT_face.py ran · metamorphic tier: invariant no licence file found · pointer only · 6c4e6da8c7866587 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Hsigmoid face_pre_pro/ViT_face.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 97e2bf83055f2f7b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Hswish face_pre_pro/ViT_face.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · aca782f4ff28c88e · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32
face_pre_pro/ViT_face.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 897a6cef897cd588 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MobileBottleneck face_pre_pro/ViT_face.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 28ab6836b172e7dd · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MobileNetV3_backbone face_pre_pro/ViT_face.py ran fingerprinted no licence file found · pointer only · 8d4ae19fb1c257ec · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Residual_droppath face_pre_pro/ViT_face.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 4b3cd3da7ae0fdbb · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
SEModule in 7 papers face_pre_pro/ViT_face.py ran · metamorphic tier: invariant no licence file found · pointer only · b2dab58cfcef1537 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Transformer in 173 papers face_pre_pro/ViT_face.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · b5f1aaa85390cced · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
conv_bn in 88 papers face_pre_pro/ViT_face.py ran · our draft was wrong no licence file found · pointer only · 3c7c350b0122c904 · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int, conv_layer:callable/0/?, norm_layer:callable/0/?, nlin_layer:callable/0/? · returned Sequential · level recorded 2026-09-22
extract_patches_pytorch_gridsample face_pre_pro/ViT_face.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 593850f8a0f901e3 · report fixture: signature imgs:Tensor/4/float, landmarks:Tensor/3/float, patch_shape:Tensor/1/float, num_landm:int/0/int · returned Tensor · level recorded 2026-09-22
make_divisible in 76 papers face_pre_pro/ViT_face.py ran · honoured contract fingerprinted no licence file found · pointer only · e122dab1d91b8c35 · report fixture: signature x:int/0/int, divisible_by:int/0/int · returned int · level recorded 2026-09-22
ViT_face_landmark_patch8_4simmin_glo_loc face_pre_pro/ViT_face.py unverified no licence file found · pointer only · 737ca9ca3ee915bd · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for LAFS (graph method: LAFS). 15 bricks; individually on a fixture: 13 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. ViT_face_landmark_patch8_4simmin_glo_loc entry · level 0 · unverified · 737ca9ca3ee915bd
  2. MobileNetV3_backbone helper · level 1 · ran · 8d4ae19fb1c257ec
  3. Transformer model · level 1 · ran · b5f1aaa85390cced
  4. extract_patches_pytorch_gridsample helper · level 1 · ran; the contract check could not run (RAISES) · 593850f8a0f901e3
  5. Hswish helper · level 1 · ran · aca782f4ff28c88e
  6. MobileBottleneck helper · level 1 · ran · 28ab6836b172e7dd
  7. conv_bn helper · level 1 · ran · our draft was wrong · 3c7c350b0122c904
  8. make_divisible helper · level 1 · ran · honoured contract · e122dab1d91b8c35
  9. Attention model · level 0 · unverified · 5eb1f008cc961666
  10. FeedForward helper · level 1 · ran · 6c4e6da8c7866587
  11. PreNorm helper · level 1 · ran · 005532cda6b215dd
  12. Residual_droppath helper · level 1 · ran · 4b3cd3da7ae0fdbb
  13. Identity helper · level 1 · ran · 897a6cef897cd588
  14. SEModule helper · level 1 · ran · b2dab58cfcef1537
  15. Hsigmoid helper · level 1 · ran · 97e2bf83055f2f7b

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2403.08161") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DiversityFace RecognitionSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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