mlsanityData to 7 Oct 2026

Improving Self-supervised Learning with Hardness-aware Dynamic Curriculum Learning: An Application to Digital Pathology

arXiv 2108.07183 ↗First posted 16 Aug 2021cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning (SSL) has recently shown tremendous potential to learn generic visual representations useful for many image analysis tasks. Despite their notable success, the existing SSL methods fail to generalize to downstream tasks when the number of labeled training instances is small or if the domain shift between the transfer domains is significant. In this paper, we attempt to improve self-supervised pretrained representations through the lens of curriculum learning by proposing a hardness-aware dynamic curriculum learning (HaDCL) approach. To improve the robustness and generalizability of SSL, we dynamically leverage progressive harder examples via easy-to-hard and hard-to-very-hard samples during mini-batch downstream fine-tuning. We discover that by progressive stage-wise curriculum learning, the pretrained representations are significantly enhanced and adaptable to both in-domain and out-of-domain distribution data. We performed extensive validation on three histology benchmark datasets on both patch-wise and slide-level classification problems. Our curriculum based fine-tuning yields a significant improvement over standard fine-tuning, with a minimum improvement in area-under-the-curve (AUC) score of 1.7% and 2.2% on in-domain and out-of-domain distribution data, respectively. Further, we empirically show that our approach is more generic and adaptable to any SSL methods and does not impose any additional overhead complexity. Besides, we also outline the role of patch-based versus slide-based curriculum learning in histopathology to provide practical insights into the success of curriculum based fine-tuning of SSL methods. Code is released at https://github.com/srinidhiPY/ICCV-CDPATH2021-ID-8

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 34 of its 41 references that are in the map. First posted on arXiv 16 Aug 2021.

Builds on

34 of 41 references.

References · 34

  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. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  4. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  5. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  6. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  7. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  8. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  9. 2020Contrastive Learning with Hard Negative Samplescited by 619
  10. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
  11. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  12. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
22 more
  1. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  2. 2021Curriculum Learning: A Surveycited by 257
  3. 2020What Should Not Be Contrastive in Contrastive Learningcited by 224
  4. 2019Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologycited by 172
  5. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
  6. 2020Self supervised contrastive learning for digital histopathologycited by 146
  7. 2020Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biasescited by 143
  8. 2018Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networkscited by 113
  9. 2020When Do Curricula Work?cited by 105
  10. 2019Accelerating Deep Learning by Focusing on the Biggest Loserscited by 94
  11. 2016Deep Learning for Identifying Metastatic Breast Cancercited by 93
  12. 2021When Does Contrastive Visual Representation Learning Work?cited by 92
  13. 2020Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotationscited by 89
  14. 2019ClusterFit: Improving Generalization of Visual Representationscited by 82
  15. 2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 81
  16. 2021The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuningcited by 74
  17. 2019Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Predictioncited by 70
  18. 2020MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Modelscited by 61
  19. 2020Learn like a Pathologist: Curriculum Learning by Annotator Agreement for Histopathology Image Classificationcited by 29
  20. 2019A Closer Look at Domain Shift for Deep Learning in Histopathologycited by 25
  21. 2020Overcoming the limitations of patch-based learning to detect cancer in whole slide imagescited by 15
  22. 2020Self-supervised Pre-training with Hard Examples Improves Visual Representationscited by 12

Built on by

Cited by year (2026 to 7 Oct)

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

13 papers.

Sort:

By area:

  1. 2023Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Imagescited by 132
  2. 2023A General-Purpose Self-Supervised Model for Computational Pathologycited by 42
  3. 2022Robust and Efficient Medical Imaging with Self-Supervisioncited by 40
  4. 2022HistoPerm: A Permutation-Based View Generation Approach for Improving Histopathologic Feature Representation Learningcited by 2
  5. 2025DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognitioncited by 2
  6. 2024Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Reviewcited by 1
  7. 2024HistoEncoder: a digital pathology foundation model for prostate cancercited by 1
  8. 2024A Survey on Cell Nuclei Instance Segmentation and Classification: Leveraging Context and Attentioncited by 0
  9. 2024Enhancing Skin Lesion Classification Generalization with Active Domain Adaptationcited by 0
  10. 2025Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Imagescited by 0
  11. 2025CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classificationcited by 0
  12. 2026Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classificationcited by 0
1 more
  1. 2026Far from the Crowd: Scalable Self-Supervised Learning via Geographic Isolationcited by 0