Face Verification

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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

Most implemented papers archive 2025-07-28

30 shown of 134 papers with code (360 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• FaceNet: A Unified Embedding for Face Recognition and Clustering
  12 Mar 2015 183 repositories listed Syntology ran 65 of 154 samples · 89 unverified · 45 pointer-only (licence)
  On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.
• ArcFace: Additive Angular Margin Loss for Deep Face Recognition
  23 Jan 2018 100 repositories listed Syntology ran 16 of 21 samples · 5 unverified · 14 pointer-only (licence)
  Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability.
• RetinaFace: Single-stage Dense Face Localisation in the Wild
  2 May 2019 76 repositories listed Syntology ran 17 of 91 samples · 74 unverified
  Face Analysis Project on MXNet
• VGGFace2: A dataset for recognising faces across pose and age
  23 Oct 2017 24 repositories listed Syntology ran 5 of 8 samples · 3 unverified · 5 pointer-only (licence)
  The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to…
• SphereFace: Deep Hypersphere Embedding for Face Recognition
  26 Apr 2017 22 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 1 pointer-only (licence)
  This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably…
• A Light CNN for Deep Face Representation with Noisy Labels
  9 Nov 2015 19 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 1 pointer-only (licence)
  This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels.
• Circle Loss: A Unified Perspective of Pair Similarity Optimization
  25 Feb 2020 16 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 1 pointer-only (licence)
  This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity sₚ and minimize the between-class similarity sₙ.
• CosFace: Large Margin Cosine Loss for Deep Face Recognition
  29 Jan 2018 11 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  The central task of face recognition, including face verification and identification, involves face feature discrimination.
• Additive Margin Softmax for Face Verification
  17 Jan 2018 10 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works.
• AdaFace: Quality Adaptive Margin for Face Recognition
  3 Apr 2022 9 repositories listed Syntology ran 17 of 22 samples · 5 unverified · 11 pointer-only (licence)
  In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality.
• DeepID3: Face Recognition with Very Deep Neural Networks
  3 Feb 2015 9 repositories listed
  Very deep neural networks recently achieved great success on general object recognition because of their superb learning capacity.
• Deep Face Recognition: A Survey
  18 Apr 2018 8 repositories listed
  Deep learning applies multiple processing layers to learn representations of data with multiple levels of feature extraction.
• GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations
  10 Apr 2023 7 repositories listed
  The development of deep learning-based biometric models that can be deployed on devices with constrained memory and computational resources has proven to be a significant challenge.
• Partial FC: Training 10 Million Identities on a Single Machine
  11 Oct 2020 7 repositories listed
  The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on…
• Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
  28 Mar 2022 6 repositories listed Syntology ran 4 of 12 samples · 8 unverified · 4 pointer-only (licence)
  In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
• SeesawFaceNets: sparse and robust face verification model for mobile platform
  24 Aug 2019 6 repositories listed Syntology ran 7 of 17 samples · 10 unverified · 5 pointer-only (licence)
  Therefore, designing lightweight networks with low memory requirement and computational cost is one of the most practical solutions for face verification on mobile platform.
• AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
  1 May 2019 6 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy.
• Sampling Matters in Deep Embedding Learning
  23 Jun 2017 6 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions.
• Deep Polynomial Neural Networks
  20 Jun 2020 5 repositories listed
  We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks.
• FacePoseNet: Making a Case for Landmark-Free Face Alignment
  24 Aug 2017 5 repositories listed
  Instead, we compare our FPN with existing methods by evaluating how they affect face recognition accuracy on the IJB-A and IJB-B benchmarks: using the same recognition pipeline, but varying the face alignment method.
• Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
  15 Dec 2016 5 repositories listed
  The 3D shapes of faces are well known to be discriminative.
• Face Detection with End-to-End Integration of a ConvNet and a 3D Model
  2 Jun 2016 5 repositories listed
  The proposed method addresses two issues in adapting state- of-the-art generic object detection ConvNets (e.
• GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition
  21 May 2020 4 repositories listed
  In the field of face recognition, a model learns to distinguish millions of face images with fewer dimensional embedding features, and such vast information may not be properly encoded in the conventional model with a…
• DeepFace: Closing the Gap to Human-Level Performance in Face Verification
  24 Jun 2014 4 repositories listed
  In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify.
• Deep Learning Face Representation from Predicting 10,000 Classes
  1 Jan 2014 4 repositories listed
  When learned as classifiers to recognize about 10, 000 face identities in the training set and configured to keep reducing the neuron numbers along the feature extraction hierarchy, these deep ConvNets gradually form…
• Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
  4 Dec 2024 3 repositories listed
  Face recognition and verification are two computer vision tasks whose performances have advanced with the introduction of deep representations.
• Controllable and Guided Face Synthesis for Unconstrained Face Recognition
  20 Jul 2022 3 repositories listed
  To address this problem, we propose a controllable face synthesis model (CFSM) that can mimic the distribution of target datasets in a style latent space.
• ElasticFace: Elastic Margin Loss for Deep Face Recognition
  20 Sep 2021 3 repositories listed
  The recent state-of-the-art face recognition solutions proposed to incorporate a fixed penalty margin on commonly used classification loss function, softmax loss, in the normalized hypersphere to increase the…
• NormFace: L2 Hypersphere Embedding for Face Verification
  21 Apr 2017 3 repositories listed
  We show that both strategies, and small variants, consistently improve performance by between 0.
• OpenFace: A general-purpose face recognition library with mobile applications
  1 Jan 2016 3 repositories listed
  Cameras are becoming ubiquitous in the Internet of Things (IoT) and can use face recognition technology to improve context.

Syntology lines on 14 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. Read from the graph 2026-09-24.