Browse State-of-the-Art › Face Verification

Face Verification

134 papers with code · 21 benchmarks · 24 datasets archive 2025-07-28

Computer Vision

Face Verification is a machine learning task in computer vision that involves determining whether two facial images belong to the same person or not. The task involves extracting features from the facial images, such as the shape and texture of the face, and then using these features to compare and verify the similarity between the images.

( Image credit: Pose-Robust Face Recognition via Deep Residual Equivariant Mapping )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

21 leaderboard tables shown for this task, 21 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 21 until expanded.

Syntology 3 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): IJB-C (1 judged, 0 placed), Labeled Faces in the Wild (3 judged, 0 placed), AgeDB-30 (1 judged, 0 placed), CFP-FP (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
IJB-C (26 rows) HeadSharing: SH-KD It's All in the Head: Representation Knowledge Distillation... code — Compare
IJB-A (17 rows) Dual-Agent GANs Dual-Agent GANs for Photorealistic and Identity Preserving Profile... — — Compare
IJB-B (12 rows) QMagFace QMagFace: Simple and Accurate Quality-Aware Face Recognition code — Compare
MegaFace (12 rows) Prodpoly Deep Polynomial Neural Networks code — Compare
YouTube Faces DB (12 rows) SeqFace, 1 ResNet-64 SeqFace: Make full use of sequence information for face recognition code — Compare
BTS3.1 (7 rows) ProxyFusion (Adaface) ProxyFusion: Face Feature Aggregation Through Sparse Experts code — Compare
Labeled Faces in the Wild (7 rows) ArcFace + MS1MV2 + R100, ArcFace: Additive Angular Margin Loss for Deep Face Recognition code Syntology official: no sample here; runs from other or unrecorded repositories · 16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified Compare
Trillion Pairs Dataset (6 rows) SV-AM-Softmax Support Vector Guided Softmax Loss for Face Recognition code — Compare
AgeDB-30 (5 rows) PartialFC(R200) Killing Two Birds with One Stone:Efficient and Robust Training of... code Syntology community repositories only · 10 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
CFP-FP (4 rows) PartialFC (R200) Killing Two Birds with One Stone:Efficient and Robust Training of... code Syntology community repositories only · 10 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
BUAA-VisNir (3 rows) LightCNN-29 + DVG Dual Variational Generation for Low-Shot Heterogeneous Face Recognition code — Compare
CASIA NIR-VIS 2.0 (3 rows) LightCNN-29 + DVG Dual Variational Generation for Low-Shot Heterogeneous Face Recognition code — Compare
LFW (3 rows) ArcFaceR50 + EM-FRR Mitigating Gender Bias in Face Recognition Using the von... code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
Oulu-CASIA NIR-VIS (3 rows) LightCNN-29 + DVG Dual Variational Generation for Low-Shot Heterogeneous Face Recognition code — Compare
CALFW (2 rows) DiscFace DiscFace: Minimum Discrepancy Learning for Deep Face Recognition — — Compare
CPLFW (2 rows) DiscFace DiscFace: Minimum Discrepancy Learning for Deep Face Recognition — — Compare
IJB-S (2 rows) AdaFace+CSFM Controllable and Guided Face Synthesis for Unconstrained Face Recognition code — Compare
CK+ (1 row) SphereFace SphereFace: Deep Hypersphere Embedding for Face Recognition code Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
IIIT-D Viewed Sketch (1 row) LightCNN-29 + DVG Dual Variational Generation for Low-Shot Heterogeneous Face Recognition code — Compare
Oulu-CASIA (1 row) DeepId2+ Deeply learned face representations are sparse, selective, and robust code — Compare
QMUL-SurvFace (1 row) DiscFace DiscFace: Minimum Discrepancy Learning for Deep Face Recognition — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

24 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 360 · with a code link: 134 · where Syntology ran a sample: 32 (27 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (32 of 360 tagged: 27 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument)

Page 1 of 4: papers 1 to 100 of 360, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 29 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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