mlsanityData to 14 Oct 2026

Learning Face Representation from Scratch

arXiv 1411.7923 ↗First posted 28 Nov 2014cs.CVcited by 453

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Pushing by big data and deep convolutional neural network (CNN), the performance of face recognition is becoming comparable to human. Using private large scale training datasets, several groups achieve very high performance on LFW, i.e., 97% to 99%. While there are many open source implementations of CNN, none of large scale face dataset is publicly available. The current situation in the field of face recognition is that data is more important than algorithm. To solve this problem, this paper proposes a semi-automatical way to collect face images from Internet and builds a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace. Based on the database, we use a 11-layer CNN to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF. The publication of CASIAWebFace will attract more research groups entering this field and accelerate the development of face recognition in the wild.

Key facts. Cited by 453 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Nov 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 98; 2022: 84; 2023: 80; 2024: 97; 2025: 55; 2026: 39.

453 papers.

Sort:

By area:

  1. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 334
  2. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 223
  3. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 193
  4. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 144
  5. 2021Adversarial Examples Make Strong Poisonscited by 119
  6. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  7. 2021SynFace: Face Recognition with Synthetic Datacited by 106
  8. 2024Arc2Face: A Foundation Model for ID-Consistent Human Facescited by 101
  9. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  10. 2023IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Modelscited by 72
  11. 2021CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiabilitycited by 69
  12. 2023BlendFace: Re-designing Identity Encoders for Face-Swappingcited by 66
38 more
  1. 2021SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distancecited by 64
  2. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  3. 2022SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Datacited by 63
  4. 2021Availability Attacks Create Shortcutscited by 62
  5. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  6. 2022Meta Balanced Network for Fair Face Recognitioncited by 53
  7. 2022Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectorscited by 47
  8. 2022M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversationcited by 47
  9. 2021Face Transformer for Recognitioncited by 46
  10. 2021Data Poisoning Won't Save You From Facial Recognitioncited by 45
  11. 2023Attribute-preserving Face Dataset Anonymization via Latent Code Optimizationcited by 43
  12. 2022WebFace260M: A Benchmark for Million-Scale Deep Face Recognitioncited by 42
  13. 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
  14. 2021Consistent Instance False Positive Improves Fairness in Face Recognitioncited by 40
  15. 2022Learning Dual Memory Dictionaries for Blind Face Restorationcited by 40
  16. 2023SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimationcited by 39
  17. 2024CLEAR: Character Unlearning in Textual and Visual Modalitiescited by 39
  18. 2023Synthetic Data for Face Recognition: Current State and Future Prospectscited by 38
  19. 2021PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillationcited by 36
  20. 2023DyGait: Exploiting Dynamic Representations for High-performance Gait Recognitioncited by 35
  21. 2021Meta-Teacher For Face Anti-Spoofingcited by 33
  22. 2023EdgeFace: Efficient Face Recognition Model for Edge Devicescited by 33
  23. 2021Deep Learning-based Face Super-Resolution: A Surveycited by 32
  24. 2021Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networkscited by 32
  25. 2021Unified Detection of Digital and Physical Face Attackscited by 31
  26. 2024Continual Forgetting for Pre-trained Vision Modelscited by 29
  27. 2022Synthetic Data in Human Analysis: A Surveycited by 28
  28. 2024SDFR: Synthetic Data for Face Recognition Competitioncited by 28
  29. 2024AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmarkcited by 28
  30. 2021About Face: A Survey of Facial Recognition Evaluationcited by 27
  31. 2022Unsupervised Face Recognition using Unlabeled Synthetic Datacited by 27
  32. 2023Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognitioncited by 27
  33. 2021FedFace: Collaborative Learning of Face Recognition Modelcited by 26
  34. 2021On the use of automatically generated synthetic image datasets for benchmarking face recognitioncited by 26
  35. 2021Face.evoLVe: A High-Performance Face Recognition Librarycited by 26
  36. 2022Face Recognition Accuracy Across Demographics: Shining a Light Into the Problemcited by 25
  37. 2021IdentityDP: Differential Private Identification Protection for Face Imagescited by 24
  38. 2021End2End Occluded Face Recognition by Masking Corrupted Featurescited by 24

50 most cited of 453 All 453 (JSON)