Papers
Topics
Authors
Recent
2000 character limit reached

Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning (2210.09452v2)

Published 17 Oct 2022 in cs.CV, cs.AI, and cs.LG

Abstract: Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-supervised learning (CSSL), which learns to push apart representations corresponding to two different randomly-selected instances. Unfortunately, in real-world applications such as medical image classification, there is often class imbalance, so randomly-selected instances mostly belong to the same majority class, which precludes CSSL from learning inter-class differences. To address this issue, we propose a novel framework, Iterative Self-paced Supervised Contrastive Learning for MIL Representations (ItS2CLR), which improves the learned representation by exploiting instance-level pseudo labels derived from the bag-level labels. The framework employs a novel self-paced sampling strategy to ensure the accuracy of pseudo labels. We evaluate ItS2CLR on three medical datasets, showing that it improves the quality of instance-level pseudo labels and representations, and outperforms existing MIL methods in terms of both bag and instance level accuracy. Code is available at https://github.com/Kangningthu/ItS2CLR

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. The cancer genome atlas program. https://www.cancer.gov/tcga, 2019.
  2. A theoretical analysis of contrastive unsupervised representation learning. arXiv preprint arXiv:1902.09229, 2019.
  3. Investigating the role of negatives in contrastive representation learning. arXiv preprint arXiv:2106.09943, 2021.
  4. Big self-supervised models advance medical image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021.
  5. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. Jama, 318(22):2199–2210, 2017.
  6. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nature medicine, 25(8):1301–1309, 2019.
  7. Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882, 2020.
  8. Emerging properties in self-supervised vision transformers. CoRR, abs/2104.14294, 2021.
  9. Self-supervised vision transformers learn visual concepts in histopathology, 2022.
  10. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  11. Multiple instance learning with center embeddings for histopathology classification. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 519–528. Springer, 2020.
  12. Pseudo-labeling curriculum for unsupervised domain adaptation. arXiv preprint arXiv:1908.00262, 2019.
  13. Debiased contrastive learning. Advances in neural information processing systems, 33:8765–8775, 2020.
  14. Self supervised contrastive learning for digital histopathology. Machine Learning with Applications, 7:100198, 2022.
  15. Alex Clark. Pillow (pil fork) documentation, 2015.
  16. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nature Medicine, 24(10):1559–1567, 2018.
  17. Classification and disease localization in histopathology using only global labels: A weakly-supervised approach. arXiv preprint arXiv:1802.02212, 2018.
  18. Self-supervision closes the gap between weak and strong supervision in histology. arXiv preprint arXiv:2012.03583, 2020.
  19. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 248–255, 2009.
  20. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations, 2020.
  21. With a little help from my friends: Nearest-neighbor contrastive learning of visual representations. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9588–9597, 2021.
  22. Deep miml network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 31, 2017.
  23. Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nature Cancer, 1(8):800–810, 2020.
  24. Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. Advances in Neural Information Processing Systems, 33:11309–11321, 2020.
  25. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, 33:21271–21284, 2020.
  26. Adaptive self-paced deep clustering with data augmentation. IEEE Transactions on Knowledge and Data Engineering, 32(9):1680–1693, 2019.
  27. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9729–9738, 2020.
  28. Deep residual learning for image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016.
  29. Attention-based deep multiple instance learning. In International conference on machine learning, pages 2127–2136. PMLR, 2018.
  30. Self-paced learning with diversity. Advances in neural information processing systems, 27, 2014.
  31. Intermediate layers matter in momentum contrastive self supervised learning. In Advances in Neural Information Processing Systems, 2021.
  32. Supervised contrastive learning. Advances in Neural Information Processing Systems, 33:18661–18673, 2020.
  33. Self-paced learning for latent variable models. Advances in neural information processing systems, 23, 2010.
  34. Weakly supervised multiple instance learning histopathological tumor segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 470–479. Springer, 2020.
  35. Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14318–14328, 2021.
  36. Adaptive early-learning correction for segmentation from noisy annotations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022.
  37. Early-learning regularization prevents memorization of noisy labels. Advances in Neural Information Processing Systems, 2020.
  38. Semi-supervised breast cancer histology classification using deep multiple instance learning and contrast predictive coding (conference presentation). In Medical Imaging 2020: Digital Pathology, volume 11320, page 113200J. International Society for Optics and Photonics, 2020.
  39. Data-efficient and weakly supervised computational pathology on whole-slide images. Nature biomedical engineering, 5(6):555–570, 2021.
  40. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018.
  41. Focus on the positives: Self-supervised learning for biodiversity monitoring. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10583–10592, 2021.
  42. From image-level to pixel-level labeling with convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1713–1721, 2015.
  43. Protomil: Multiple instance learning with prototypical parts for fine-grained interpretability. ArXiv, abs/2108.10612, 2021.
  44. Transmil: Transformer based correlated multiple instance learning for whole slide image classification. Advances in Neural Information Processing Systems, 34, 2021.
  45. Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams. Nature communications, 12(1):1–13, 2021.
  46. An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization. Medical image analysis, 68:101908, 2021.
  47. Structure-preserving color normalization and sparse stain separation for histological images. IEEE Transactions on Medical Imaging, 35(8):1962–1971, 2016.
  48. Solving inefficiency of self-supervised representation learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9505–9515, 2021.
  49. Theoretical analysis of self-training with deep networks on unlabeled data. In International Conference on Learning Representations, 2020.
  50. Camel: A weakly supervised learning framework for histopathology image segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10682–10691, 2019.
  51. Barlow twins: Self-supervised learning via redundancy reduction. arXiv preprint arXiv:2103.03230, 2021.
  52. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34, 2021.
  53. Dtfd-mil: Double-tier feature distillation multiple instance learning for histopathology whole slide image classification. arXiv preprint arXiv:2203.12081, 2022.
  54. Curriculum domain adaptation for semantic segmentation of urban scenes. In Proceedings of the IEEE international conference on computer vision, pages 2020–2030, 2017.
  55. Unsupervised domain adaptation with noise resistible mutual-training for person re-identification. In European Conference on Computer Vision, pages 526–544. Springer, 2020.
  56. Weakly supervised contrastive learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10042–10051, 2021.
  57. Graph convolutional label noise cleaner: Train a plug-and-play action classifier for anomaly detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1237–1246, 2019.
  58. Interpretable prediction of lung squamous cell carcinoma recurrence with self-supervised learning. In Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, volume 172 of Proceedings of Machine Learning Research, pages 1504–1522. PMLR, 06–08 Jul 2022.
  59. Domain adaptation for semantic segmentation via class-balanced self-training. arXiv preprint arXiv:1810.07911, 2018.
  60. Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European conference on computer vision, pages 289–305, 2018.
Citations (18)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Slide Deck Streamline Icon: https://streamlinehq.com

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up