mlsanityData to 7 Oct 2026

Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining

arXiv 2308.04551 ↗First posted 8 Aug 2023eess.IV cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Noisy labels hurt deep learning-based supervised image classification performance as the models may overfit the noise and learn corrupted feature extractors. For natural image classification training with noisy labeled data, model initialization with contrastive self-supervised pretrained weights has shown to reduce feature corruption and improve classification performance. However, no works have explored: i) how other self-supervised approaches, such as pretext task-based pretraining, impact the learning with noisy label, and ii) any self-supervised pretraining methods alone for medical images in noisy label settings. Medical images often feature smaller datasets and subtle inter class variations, requiring human expertise to ensure correct classification. Thus, it is not clear if the methods improving learning with noisy labels in natural image datasets such as CIFAR would also help with medical images. In this work, we explore contrastive and pretext task-based self-supervised pretraining to initialize the weights of a deep learning classification model for two medical datasets with self-induced noisy labels -- NCT-CRC-HE-100K tissue histological images and COVID-QU-Ex chest X-ray images. Our results show that models initialized with pretrained weights obtained from self-supervised learning can effectively learn better features and improve robustness against noisy labels.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 8 Aug 2023.

Builds on

31 of 44 references.

References · 31

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  5. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  6. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  8. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  9. 2016Colorful Image Colorizationcited by 1,113
  10. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  11. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  12. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
19 more
  1. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  2. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  3. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  4. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  5. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  6. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  7. 2017Colorization as a Proxy Task for Visual Understandingcited by 175
  8. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  9. 2020Predicting What You Already Know Helps: Provable Self-Supervised Learningcited by 152
  10. 2020Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotationscited by 89
  11. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  12. 2019Robust Inference via Generative Classifiers for Handling Noisy Labelscited by 67
  13. 2020Interpreting Chest X-rays via CNNs that Exploit Hierarchical Disease Dependencies and Uncertainty Labelscited by 56
  14. 2019How does Early Stopping Help Generalization against Label Noise?cited by 41
  15. 2019Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classificationcited by 33
  16. 2022Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-trainingcited by 21
  17. 2021Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correctioncited by 16
  18. 2021How Does Heterogeneous Label Noise Impact Generalization in Neural Nets?cited by 3
  19. 2021CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learningcited by 3

Built on by

Cited by year

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

8 papers.

  1. 2024QMix: Quality-aware Learning with Mixed Noise for Robust Retinal Disease Diagnosiscited by 5
  2. 2024Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noisecited by 3
  3. 2025Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlookcited by 3
  4. 2024How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?cited by 1
  5. 2024Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image Classificationcited by 1
  6. 2023Sample selection with noise rate estimation in noise learning of medical image analysiscited by 0
  7. 2024Divergent Domains, Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Gradingcited by 0
  8. 2025Local K-Similarity Constraint for Federated Learning with Label Noisecited by 0