mlsanityData to 14 Oct 2026

A View From Somewhere: Human-Centric Face Representations

arXiv 2303.17176 ↗First posted 30 Mar 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Few datasets contain self-identified sensitive attributes, inferring attributes risks introducing additional biases, and collecting attributes can carry legal risks. Besides, categorical labels can fail to reflect the continuous nature of human phenotypic diversity, making it difficult to compare the similarity between same-labeled faces. To address these issues, we present A View From Somewhere (AVFS) -- a dataset of 638,180 human judgments of face similarity. We demonstrate the utility of AVFS for learning a continuous, low-dimensional embedding space aligned with human perception. Our embedding space, induced under a novel conditional framework, not only enables the accurate prediction of face similarity, but also provides a human-interpretable decomposition of the dimensions used in the human-decision making process, and the importance distinct annotators place on each dimension. We additionally show the practicality of the dimensions for collecting continuous attributes, performing classification, and comparing dataset attribute disparities.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 38 of its 111 references that are in the map. First posted on arXiv 30 Mar 2023.

Builds on

38 of 111 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  10. 2018Datasheets for Datasetscited by 1,386
  11. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  12. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
26 more
  1. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  2. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
  3. 2014Learning Face Representation from Scratchcited by 453
  4. 2020Large image datasets: A pyrrhic win for computer vision?cited by 237
  5. 2019Towards a Critical Race Methodology in Algorithmic Fairnesscited by 125
  6. 2021Understanding and Evaluating Racial Biases in Image Captioningcited by 108
  7. 2020Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biasescited by 107
  8. 2021Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Researchcited by 102
  9. 2021Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Developmentcited by 85
  10. 2021A Study of Face Obfuscation in ImageNetcited by 83
  11. 2020Face Recognition: Too Bias, or Not Too Bias?cited by 82
  12. 2021Towards Measuring Fairness in AI: the Casual Conversations Datasetcited by 80
  13. 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80
  14. 2020Lifespan Age Transformation Synthesiscited by 60
  15. 2020"What We Can't Measure, We Can't Understand": Challenges to Demographic Data Procurement in the Pursuit of Fairnesscited by 56
  16. 2021Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotationcited by 52
  17. 2021PASS: An ImageNet replacement for self-supervised pretraining without humanscited by 51
  18. 2021Understanding and Mitigating Annotation Bias in Facial Expression Recognitioncited by 50
  19. 2018Racial categories in machine learningcited by 48
  20. 2021A Step Toward More Inclusive People Annotations for Fairnesscited by 46
  21. 2018A Compact Embedding for Facial Expression Similaritycited by 41
  22. 2020Enriching ImageNet with Human Similarity Judgments and Psychological Embeddingscited by 23
  23. 2021UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Modelscited by 23
  24. 2019Revealing interpretable object representations from human behaviorcited by 17
  25. 2020Transforming Neural Network Visual Representations to Predict Human Judgments of Similaritycited by 16
  26. 2018Finding your Lookalike: Measuring Face Similarity Rather than Face Identitycited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 1.

6 papers.

  1. 2023Consensus and Subjectivity of Skin Tone Annotation for ML Fairnesscited by 22
  2. 2023Are demographically invariant models and representations in medical imaging fair?cited by 6
  3. 2024Generalized People Diversity: Learning a Human Perception-Aligned Diversity Representation for People Imagescited by 6
  4. 2024A Taxonomy of Challenges to Curating Fair Datasetscited by 2
  5. 2024Multi-Group Proportional Representation in Retrievalcited by 2
  6. 2025A Comparison of Human and Machine Learning Errors in Face Recognitioncited by 1