Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Leveraging Old Knowledge to Continually Learn New Classes in Medical Images (2303.13752v1)

Published 24 Mar 2023 in cs.LG, cs.CV, and eess.IV

Abstract: Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned. This is especially needed in the medical domain where continually learning from new incoming data is required to classify an expanded set of diseases. In this work, we focus on how old knowledge can be leveraged to learn new classes without catastrophic forgetting. We propose a framework that comprises of two main components: (1) a dynamic architecture with expanding representations to preserve previously learned features and accommodate new features; and (2) a training procedure alternating between two objectives to balance the learning of new features while maintaining the model's performance on old classes. Experiment results on multiple medical datasets show that our solution is able to achieve superior performance over state-of-the-art baselines in terms of class accuracy and forgetting.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Memory aware synapses: Learning what (not) to forget. In Proceedings of the European Conference on Computer Vision (ECCV), 139–154.
  2. Online Continual Learning with Maximal Interfered Retrieval. In Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc.
  3. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nature medicine, 25(6): 954–961.
  4. End-to-end incremental learning. In Proceedings of the European conference on computer vision (ECCV), 233–248.
  5. Using hindsight to anchor past knowledge in continual learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 6993–7001.
  6. On Tiny Episodic Memories in Continual Learning. arXiv:1902.10486.
  7. EyePACS: an adaptable telemedicine system for diabetic retinopathy screening. Journal of diabetes science and technology, 3(3): 509–516.
  8. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9268–9277.
  9. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, 248–255. IEEE.
  10. Podnet: Pooled outputs distillation for small-tasks incremental learning. In European Conference on Computer Vision, 86–102. Springer.
  11. Pediatric T-and NK-cell lymphomas: new biologic insights and treatment strategies. Blood Cancer Journal, 2(4): e65–e65.
  12. Dermatologist-level classification of skin cancer with deep neural networks. nature, 542(7639): 115–118.
  13. Pathnet: Evolution channels gradient descent in super neural networks. arXiv:1701.08734.
  14. An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks. In 2nd International Conference on Learning Representations (ICLR), Conference Track Proceedings.
  15. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778.
  16. Lifelong learning via progressive distillation and retrospection. In Proceedings of the European Conference on Computer Vision (ECCV), 437–452.
  17. Learning a unified classifier incrementally via rebalancing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 831–839.
  18. Compacting, picking and growing for unforgetting continual learning. Advances in Neural Information Processing Systems, 32.
  19. Kaggle; and EyePacs. 2015. Kaggle Diabetic Retinopathy Detection. https://www.kaggle.com/c/diabetic-retinopathy-detection/data. Accessed: 2022-02-20.
  20. Multi-class texture analysis in colorectal cancer histology. Scientific reports, 6: 27988.
  21. Split-and-bridge: Adaptable class incremental learning within a single neural network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 8137–8145.
  22. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13): 3521–3526.
  23. On information and sufficiency. The annals of mathematical statistics, 22(1): 79–86.
  24. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence, 40(12): 2935–2947.
  25. Continual learning of new diseases with dual distillation and ensemble strategy. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 169–178. Springer.
  26. Mnemonics training: Multi-class incremental learning without forgetting. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, 12245–12254.
  27. Piggyback: Adapting a single network to multiple tasks by learning to mask weights. In Proceedings of the European Conference on Computer Vision (ECCV), 67–82.
  28. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation, volume 24, 109–165. Elsevier.
  29. International evaluation of an AI system for breast cancer screening. Nature, 577(7788): 89–94.
  30. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
  31. Continual unsupervised representation learning. Advances in Neural Information Processing Systems, 32.
  32. iCaRL: Incremental classifier and representation learning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2001–2010.
  33. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. International Journal of Computer Vision, 128: 336–359.
  34. Online class-incremental continual learning with adversarial shapley value. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 9630–9638.
  35. Continual learning with deep generative replay. Advances in neural information processing systems, 30.
  36. Topology-preserving class-incremental learning. In European Conference on Computer Vision, 254–270. Springer.
  37. Ting, K. M. 2000. A comparative study of cost-sensitive boosting algorithms. In Proceedings of the 17th International Conference on Machine Learning. Citeseer.
  38. Tschandl, P. 2018. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. https://doi.org/10.7910/DVN/DBW86T. Accessed: 2022-04-04.
  39. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data, 5(1): 1–9.
  40. Continual learning through retrieval and imagination. In AAAI Conference on Artificial Intelligence, volume 8.
  41. Welling, M. 2009. Herding dynamical weights to learn. In Proceedings of the 26th Annual International Conference on Machine Learning, 1121–1128.
  42. Memory replay gans: Learning to generate new categories without forgetting. Advances in Neural Information Processing Systems, 31.
  43. Large scale incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 374–382.
  44. Der: Dynamically expandable representation for class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3014–3023.
  45. Continual learning with bayesian model based on a fixed pre-trained feature extractor. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 397–406. Springer.
  46. Lifelong learning with dynamically expandable networks. arXiv:1708.01547.
  47. Dermoscopy of Dermatofibromas: A Prospective Morphological Study of 412 Cases. Archives of Dermatology, 144(1): 75–83.
  48. Continual learning through synaptic intelligence. In International Conference on Machine Learning, 3987–3995. PMLR.
  49. Maintaining discrimination and fairness in class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13208–13217.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Evelyn Chee (2 papers)
  2. Mong Li Lee (15 papers)
  3. Wynne Hsu (32 papers)
Citations (7)
View on Semantic Scholar

Summary

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

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