mlsanityData to 7 Oct 2026

Searching for Alignment in Face Recognition

arXiv 2102.05447 ↗First posted 10 Feb 2021cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing. Among them, face detection, landmark detection and representation learning have long been studied and a lot of works have been proposed. As an essential step with a significant impact on recognition performance, the alignment step has attracted little attention. In this paper, we first explore and highlight the effects of different alignment templates on face recognition. Then, for the first time, we try to search for the optimal template automatically. We construct a well-defined searching space by decomposing the template searching into the crop size and vertical shift, and propose an efficient method Face Alignment Policy Search (FAPS). Besides, a well-designed benchmark is proposed to evaluate the searched policy. Experiments on our proposed benchmark validate the effectiveness of our method to improve face recognition performance.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 10 Feb 2021.

Builds on

29 of 45 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  4. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  5. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  6. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  7. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  8. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 516
  9. 2014Learning Face Representation from Scratchcited by 451
  10. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  11. 2017Population Based Training of Neural Networkscited by 351
  12. 2017Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environmentscited by 258
17 more
  1. 2019Fast AutoAugmentcited by 243
  2. 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
  3. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  4. 2014Deep Learning Face Representation by Joint Identification-Verificationcited by 162
  5. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  6. 2017S3FD: Single Shot Scale-invariant Face Detectorcited by 142
  7. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 129
  8. 2019Adversarial AutoAugmentcited by 111
  9. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  10. 2019DetNAS: Backbone Search for Object Detectioncited by 80
  11. 2020Learning Meta Face Recognition in Unseen Domainscited by 61
  12. 2014Deeply learned face representations are sparse, selective, and robustcited by 56
  13. 2015Targeting Ultimate Accuracy: Face Recognition via Deep Embeddingcited by 18
  14. 2018Face Synthesis for Eyeglass-Robust Face Recognitioncited by 12
  15. 2018Large-scale Bisample Learning on ID Versus Spot Face Recognitioncited by 9
  16. 2019Attentional Feature-Pair Relation Networks for Accurate Face Recognitioncited by 9
  17. 2018GridFace: Face Rectification via Learning Local Homography Transformationscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 1; 2024: 1; 2025: 1; 2026: 1.

12 papers.

  1. 2021Learning Compatible Embeddingscited by 37
  2. 2022Improving Federated Learning Face Recognition via Privacy-Agnostic Clusterscited by 18
  3. 2021PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognitioncited by 7
  4. 2023GaitFormer: Learning Gait Representations with Noisy Multi-Task Learningcited by 7
  5. 2024ARoFace: Alignment Robustness to Improve Low-Quality Face Recognitioncited by 4
  6. 2021Prototype Memory for Large-scale Face Representation Learningcited by 3
  7. 2022Towards Privacy-Preserving, Real-Time and Lossless Feature Matchingcited by 2
  8. 2022Basket-based Softmaxcited by 1
  9. 2025Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignmentcited by 1
  10. 2022Adaptive Discriminative Regularization for Visual Classificationcited by 0
  11. 2022Robust Boosting Forests with Richer Deep Feature Hierarchycited by 0
  12. 2026Generalization Limits in Vehicle Re-Identificationcited by 0