mlsanityData to 14 Oct 2026

CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions

arXiv 2208.13528 ↗First posted 29 Aug 2022cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

While deep learning based approaches have demonstrated expert-level performance in dermatological diagnosis tasks, they have also been shown to exhibit biases toward certain demographic attributes, particularly skin types (e.g., light versus dark), a fairness concern that must be addressed. We propose CIRCLe, a skin color invariant deep representation learning method for improving fairness in skin lesion classification. CIRCLe is trained to classify images by utilizing a regularization loss that encourages images with the same diagnosis but different skin types to have similar latent representations. Through extensive evaluation and ablation studies, we demonstrate CIRCLe's superior performance over the state-of-the-art when evaluated on 16k+ images spanning 6 Fitzpatrick skin types and 114 diseases, using classification accuracy, equal opportunity difference (for light versus dark groups), and normalized accuracy range, a new measure we propose to assess fairness on multiple skin type groups.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 25 of its 60 references that are in the map. First posted on arXiv 29 Aug 2022.

Builds on

25 of 60 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  8. 2019Searching for MobileNetV3cited by 1,994
  9. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  10. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  11. 2013Domain Generalization via Invariant Feature Representationcited by 623
  12. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
13 more
  1. 2019BCN20000: Dermoscopic Lesions in the Wildcited by 225
  2. 2021Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Datasetcited by 185
  3. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  4. 2020A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Contextcited by 146
  5. 2020Algorithmic Fairnesscited by 143
  6. 2021Disparities in Dermatology AI: Assessments Using Diverse Clinical Imagescited by 134
  7. 2019A deep learning system for differential diagnosis of skin diseasescited by 118
  8. 2020PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphonescited by 118
  9. 2022FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosiscited by 59
  10. 2021Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentationcited by 57
  11. 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
  12. 2022Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classificationcited by 23
  13. 2022Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionarycited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 4; 2025: 5; 2026: 2.

17 papers.

Sort:

By area:

  1. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 48
  2. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  3. 2022Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Reviewcited by 28
  4. 2023Are Sex-based Physiological Differences the Cause of Gender Bias for Chest X-ray Diagnosis?cited by 13
  5. 2023GIST: Generating Image-Specific Text for Fine-grained Object Classificationcited by 8
  6. 2024Prompt-driven Latent Domain Generalization for Medical Image Classificationcited by 8
  7. 2024Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasetscited by 7
  8. 2024Learning Color Equivariant Representationscited by 5
  9. 2023Assessing the Generalizability of Deep Neural Networks-Based Models for Black Skin Lesionscited by 3
  10. 2024APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigationcited by 2
  11. 2025Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learningcited by 2
  12. 2025Evaluating Fairness and Mitigating Bias in Machine Learning: A Novel Technique using Tensor Data and Bayesian Regressioncited by 1
5 more
  1. 2026A Hypertoroidal Covering for Perfect Color Equivariancecited by 1
  2. 2025The Impact of Skin Tone Label Granularity on the Performance and Fairness of AI Based Dermatology Image Classification Modelscited by 0
  3. 2025Fitzpatrick Thresholding for Skin Image Segmentationcited by 0
  4. 2025Mitigating Individual Skin Tone Bias in Skin Lesion Classification through Distribution-Aware Reweightingcited by 0
  5. 2026Exploring the Impact of Skin Color on Skin Lesion Segmentationcited by 0