mlsanityData to 7 Oct 2026

Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification

arXiv 2109.09818 ↗First posted 20 Sep 2021cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks have demonstrated dermatologist-level performance in the classification of melanoma from skin lesion images, but prediction irregularities due to biases seen within the training data are an issue that should be addressed before widespread deployment is possible. In this work, we robustly remove bias and spurious variation from an automated melanoma classification pipeline using two leading bias unlearning techniques. We show that the biases introduced by surgical markings and rulers presented in previous studies can be reasonably mitigated using these bias removal methods. We also demonstrate the generalisation benefits of unlearning spurious variation relating to the imaging instrument used to capture lesion images. Our experimental results provide evidence that the effects of each of the aforementioned biases are notably reduced, with different debiasing techniques excelling at different tasks.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 20 Sep 2021.

Builds on

24 of 47 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  10. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  11. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  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
12 more
  1. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  2. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  3. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  4. 2020A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Contextcited by 146
  5. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 122
  6. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  7. 2020Debiasing Skin Lesion Datasets and Models? Not So Fastcited by 43
  8. 2019(De)Constructing Bias on Skin Lesion Datasetscited by 30
  9. 2020Identifying Melanoma Images using EfficientNet Ensemble: Winning Solution to the SIIM-ISIC Melanoma Classification Challengecited by 24
  10. 2017Skin Lesion Analysis Towards Melanoma Detection Using Deep Learning Networkcited by 21
  11. 2016An Overview of Melanoma Detection in Dermoscopy Images Using Image Processing and Machine Learningcited by 13
  12. 2020Camera Bias in a Fine Grained Classification Taskcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 5; 2024: 4; 2025: 2; 2026: 3.

18 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  2. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  3. 2022Deep Regression Unlearningcited by 32
  4. 2022The (de)biasing effect of GAN-based augmentation methods on skin lesion imagescited by 9
  5. 2023Revisiting Skin Tone Fairness in Dermatological Lesion Classificationcited by 9
  6. 2024BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuningcited by 6
  7. 2023Data AUDIT: Identifying Attribute Utility- and Detectability-Induced Bias in Task Modelscited by 4
  8. 2024On Biases in a UK Biobank-based Retinal Image Classification Modelcited by 4
  9. 2022A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysiscited by 3
  10. 2023Removing confounding information from fetal ultrasound imagescited by 3
  11. 2024Dataset Distribution Impacts Model Fairness: Single vs. Multi-Task Learningcited by 2
  12. 2022Siamese Neural Networks for Skin Cancer Classification and New Class Detection using Clinical and Dermoscopic Image Datasetscited by 1
6 more
  1. 2024Unlearning-based Neural Interpretationscited by 0
  2. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  3. 2025SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigationcited by 0
  4. 2026LesionTABE: Equitable AI for Skin Lesion Detectioncited by 0
  5. 2026Effect of Demographic Bias on Skin Lesion Classificationcited by 0
  6. 2026SpurCon: Weighted Supervised Contrastive Learning for Mitigating Spurious Cues in Medical Imagingcited by 0