mlsanityData to 13 Oct 2026

ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition

arXiv 2407.14972 ↗First posted 20 Jul 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Aiming to enhance Face Recognition (FR) on Low-Quality (LQ) inputs, recent studies suggest incorporating synthetic LQ samples into training. Although promising, the quality factors that are considered in these works are general rather than FR-specific, eg, atmospheric turbulence, resolution, etc. Motivated by the observation of the vulnerability of current FR models to even small Face Alignment Errors (FAE) in LQ images, we present a simple yet effective method that considers FAE as another quality factor that is tailored to FR. We seek to improve LQ FR by enhancing FR models' robustness to FAE. To this aim, we formalize the problem as a combination of differentiable spatial transformations and adversarial data augmentation in FR. We perturb the alignment of the training samples using a controllable spatial transformation and enrich the training with samples expressing FAE. We demonstrate the benefits of the proposed method by conducting evaluations on IJB-B, IJB-C, IJB-S (+4.3% Rank1), and TinyFace (+2.63%). hrefhttps://github.com/msed-Ebrahimi/ARoFacehttps://github.com/msed-Ebrahimi/ARoFace

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 59 of its 87 references that are in the map. First posted on arXiv 20 Jul 2024.

Builds on

59 of 87 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,336
  4. 2016Densely Connected Convolutional Networkscited by 6,707
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,379
  6. 2015Spatial Transformer Networkscited by 1,425
  7. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 970
  8. 2016Adversarial Machine Learning at Scalecited by 935
  9. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 898
  10. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 735
  11. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 624
  12. 2014Learning Face Representation from Scratchcited by 453
38 more
  1. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
  2. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 334
  3. 2018Feature Denoising for Improving Adversarial Robustnesscited by 313
  4. 2019Adversarial Examples Improve Image Recognitioncited by 284
  5. 2017Data Augmentation Generative Adversarial Networkscited by 278
  6. 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
  7. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 223
  8. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  9. 2018Spatially Transformed Adversarial Examplescited by 195
  10. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 174
  11. 2016View Synthesis by Appearance Flowcited by 172
  12. 2019Probabilistic Face Embeddingscited by 172
  13. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  14. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 162
  15. 2018Deep Learning for Single Image Super-Resolution: A Brief Reviewcited by 158
  16. 2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
  17. 2019Implicit Semantic Data Augmentation for Deep Networkscited by 106
  18. 2021Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognitioncited by 96
  19. 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 88
  20. 2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
  21. 2020Towards Universal Representation Learning for Deep Face Recognitioncited by 78
  22. 2017Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesiscited by 75
  23. 2019Progressive Face Super-Resolution via Attention to Facial Landmarkcited by 73
  24. 2021CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiabilitycited by 69
  25. 2018Low-Resolution Face Recognitioncited by 64
  26. 2019AdvFaces: Adversarial Face Synthesiscited by 60
  27. 2020Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimationcited by 53
  28. 2018Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimationcited by 44
  29. 2022AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic Modelscited by 34
  30. 2023Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentationcited by 27
  31. 2021QMagFace: Simple and Accurate Quality-Aware Face Recognitioncited by 25
  32. 2016WarpNet: Weakly Supervised Matching for Single-view Reconstructioncited by 22
  33. 2018Fast Geometrically-Perturbed Adversarial Facescited by 22
  34. 2022Controllable and Guided Face Synthesis for Unconstrained Face Recognitioncited by 22
  35. 2022Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognitioncited by 22
  36. 2019Dual Directed Capsule Network for Very Low Resolution Image Recognitioncited by 20
  37. 2017Low Resolution Face Recognition Using a Two-Branch Deep Convolutional Neural Network Architecturecited by 17
  38. 2023A Quality Aware Sample-to-Sample Comparison for Face Recognitioncited by 17

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.