mlsanityData to 14 Oct 2026

Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysis

arXiv 2409.19582 ↗First posted 29 Sep 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

In this work, we explore Self-supervised Learning (SSL) as an auxiliary task to blend the texture-based local descriptors into feature modelling for efficient face analysis. Combining a primary task and a self-supervised auxiliary task is beneficial for robust representation. Therefore, we used the SSL task of mask auto-encoder (MAE) as an auxiliary task to reconstruct texture features such as local patterns along with the primary task for robust and unbiased face analysis. We experimented with our hypothesis on three major paradigms of face analysis: face attribute and face-based emotion analysis, and deepfake detection. Our experiment results exhibit that better feature representation can be gleaned from our proposed model for fair and bias-less face analysis.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 51 of its 86 references that are in the map. First posted on arXiv 29 Sep 2024.

Builds on

51 of 86 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  10. 2014Going Deeper with Convolutionscited by 4,241
  11. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
38 more
  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  3. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  5. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  6. 2021ViViT: A Video Vision Transformercited by 1,620
  7. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  8. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  9. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  10. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  11. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  12. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  13. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  14. 2021Multiscale Vision Transformerscited by 897
  15. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  16. 2017AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wildcited by 492
  17. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  18. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
  19. 2014Deep Learning Face Representation by Joint Identification-Verificationcited by 162
  20. 2019Rank consistent ordinal regression for neural networks with application to age estimationcited by 133
  21. 2021Vision Transformer for Small-Size Datasetscited by 122
  22. 2021Efficient Training of Visual Transformers with Small Datasetscited by 108
  23. 2022ConvMAE: Masked Convolution Meets Masked Autoencoderscited by 105
  24. 2016HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognitioncited by 104
  25. 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
  26. 2020LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihoodcited by 87
  27. 2021Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regressioncited by 58
  28. 2016An All-In-One Convolutional Neural Network for Face Analysiscited by 45
  29. 2023STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detectioncited by 43
  30. 2016Local Binary Convolutional Neural Networkscited by 38
  31. 2022How to Train Vision Transformer on Small-scale Datasets?cited by 35
  32. 2019Face Parsing with RoI Tanh-Warpingcited by 33
  33. 2022Locality Guidance for Improving Vision Transformers on Tiny Datasetscited by 33
  34. 2023Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoderscited by 17
  35. 2021HIH: Towards More Accurate Face Alignment via Heatmap in Heatmapcited by 15
  36. 2020Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharingcited by 8
  37. 2019Dynamic Multi-Task Learning for Face Recognition with Facial Expressioncited by 6
  38. 2021Segmentation-Reconstruction-Guided Facial Image De-occlusioncited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

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

3 papers.

  1. 2025Do You See What I Say? Generalizable Deepfake Detection based on Visual Speech Recognitioncited by 0
  2. 2026Fusion-SSAT: Unleashing the Potential of Self-supervised Auxiliary Task by Feature Fusion for Generalized Deepfake Detectioncited by 0
  3. 2026A Backbone Benchmarking Study on Self-supervised Learning as a Auxiliary Task with Texture-based Local Descriptors for Face Analysiscited by 0