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
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation (2311.17325v2)

Published 29 Nov 2023 in cs.CV

Abstract: Semi-supervised medical image segmentation studies have shown promise in training models with limited labeled data. However, current dominant teacher-student based approaches can suffer from the confirmation bias. To address this challenge, we propose AD-MT, an alternate diverse teaching approach in a teacher-student framework. It involves a single student model and two non-trainable teacher models that are momentum-updated periodically and randomly in an alternate fashion. To mitigate the confirmation bias from the diverse supervision, the core of AD-MT lies in two proposed modules: the Random Periodic Alternate (RPA) Updating Module and the Conflict-Combating Module (CCM). The RPA schedules the alternating diverse updating process with complementary data batches, distinct data augmentation, and random switching periods to encourage diverse reasoning from different teaching perspectives. The CCM employs an entropy-based ensembling strategy to encourage the model to learn from both the consistent and conflicting predictions between the teachers. Experimental results demonstrate the effectiveness and superiority of our AD-MT on the 2D and 3D medical segmentation benchmarks across various semi-supervised settings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Pseudo-labeling and confirmation bias in deep semi-supervised learning. In 2020 International Joint Conference on Neural Networks. IEEE, 2020.
  2. Bidirectional copy-paste for semi-supervised medical image segmentation. arXiv preprint arXiv:2305.00673, 2023.
  3. Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE transactions on medical imaging, 37(11):2514–2525, 2018.
  4. Mixmatch: A holistic approach to semi-supervised learning. In Adv. Neural Inform. Process. Syst., 2019.
  5. Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. In International Conference on Learning Representations, 2020.
  6. Swin-unet: Unet-like pure transformer for medical image segmentation. In Eur. Conf. Comput. Vis. Springer, 2022.
  7. Semi-supervised semantic segmentation with cross pseudo supervision. In IEEE Conf. Comput. Vis. Pattern Recog., 2021.
  8. Randaugment: Practical automated data augmentation with a reduced search space. In IEEE Conf. Comput. Vis. Pattern Recog. workshops, pages 702–703, 2020.
  9. Simple copy-paste is a strong data augmentation method for instance segmentation. In IEEE Conf. Comput. Vis. Pattern Recog., 2021.
  10. Semi-supervised semantic segmentation with error localization network. In IEEE Conf. Comput. Vis. Pattern Recog., 2022.
  11. Semi-supervised medical image segmentation using adversarial consistency learning and dynamic convolution network. IEEE Transactions on Medical Imaging, 2022.
  12. Shape-aware semi-supervised 3d semantic segmentation for medical images. In Medical Image Computing and Computer Assisted Intervention, pages 552–561. Springer, 2020.
  13. Cfcg: Semi-supervised semantic segmentation via cross-fusion and contour guidance supervision. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16348–16358, 2023.
  14. Perturbed and strict mean teachers for semi-supervised semantic segmentation. In IEEE Conf. Comput. Vis. Pattern Recog., 2022.
  15. Semi-supervised semantic segmentation via strong-weak dual-branch network. In Eur. Conf. Comput. Vis., 2020.
  16. Semi-supervised medical image segmentation through dual-task consistency. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 8801–8809, 2021a.
  17. Efficient semi-supervised gross target volume of nasopharyngeal carcinoma segmentation via uncertainty rectified pyramid consistency. In Medical Image Computing and Computer Assisted Interventio, pages 318–329. Springer, 2021b.
  18. Semi-supervised medical image segmentation via cross teaching between cnn and transformer. In International Conference on Medical Imaging with Deep Learning, pages 820–833. PMLR, 2022.
  19. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV), pages 565–571. Ieee, 2016.
  20. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence, 41(8):1979–1993, 2018.
  21. Switching temporary teachers for semi-supervised semantic segmentation. arXiv preprint arXiv:2310.18640, 2023.
  22. U-net: Convolutional networks for biomedical image segmentation. In MICCAI, 2015.
  23. Deeporgan: Multi-level deep convolutional networks for automated pancreas segmentation. In Medical Image Computing and Computer-Assisted Intervention, pages 556–564. Springer, 2015.
  24. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685, 2020.
  25. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. arXiv preprint arXiv:1703.01780, 2017.
  26. Jeya Maria Jose Valanarasu and Vishal M Patel. Unext: Mlp-based rapid medical image segmentation network. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part V, pages 23–33. Springer, 2022.
  27. Mcf: Mutual correction framework for semi-supervised medical image segmentation. In IEEE Conf. Comput. Vis. Pattern Recog., pages 15651–15660, 2023a.
  28. Conflict-based cross-view consistency for semi-supervised semantic segmentation. In IEEE Conf. Comput. Vis. Pattern Recog., 2023b.
  29. Semi-supervised left atrium segmentation with mutual consistency training. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part II 24, pages 297–306. Springer, 2021.
  30. Mutual consistency learning for semi-supervised medical image segmentation. Medical Image Analysis, 81:102530, 2022a.
  31. Exploring smoothness and class-separation for semi-supervised medical image segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part V, pages 34–43. Springer, 2022b.
  32. Fussnet: Fusing two sources of uncertainty for semi-supervised medical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 481–491. Springer, 2022.
  33. Unsupervised data augmentation for consistency training. arXiv preprint arXiv:1904.12848, 2019.
  34. A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging. Medical image analysis, 67:101832, 2021.
  35. After-unet: Axial fusion transformer unet for medical image segmentation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 3971–3981, 2022.
  36. St++: Make self-training work better for semi-supervised semantic segmentation. In IEEE Conf. Comput. Vis. Pattern Recog., 2022.
  37. Revisiting weak-to-strong consistency in semi-supervised semantic segmentation. In IEEE Conf. Comput. Vis. Pattern Recog., pages 7236–7246, 2023.
  38. Bootstrapping semi-supervised medical image segmentation with anatomical-aware contrastive distillation. In International Conference on Information Processing in Medical Imaging, pages 641–653. Springer, 2023.
  39. Uncertainty-aware self-ensembling model for semi-supervised 3d left atrium segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 605–613. Springer, 2019.
  40. A simple baseline for semi-supervised semantic segmentation with strong data augmentation. In Int. Conf. Comput. Vis., 2021.
  41. Dc-ssl: Addressing mismatched class distribution in semi-supervised learning. In IEEE Conf. Comput. Vis. Pattern Recog., 2022a.
  42. Lassl: Label-guided self-training for semi-supervised learning. In AAAI, 2022b.
  43. Instance-specific and model-adaptive supervision for semi-supervised semantic segmentation. In IEEE Conf. Comput. Vis. Pattern Recog., pages 23705–23714, 2023a.
  44. Augmentation matters: A simple-yet-effective approach to semi-supervised semantic segmentation. In IEEE Conf. Comput. Vis. Pattern Recog., pages 11350–11359, 2023b.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Zhen Zhao (85 papers)
  2. Zicheng Wang (26 papers)
  3. Longyue Wang (87 papers)
  4. Yixuan Yuan (68 papers)
  5. Luping Zhou (72 papers)
  6. Dian Yu (78 papers)
Citations (4)
View on Semantic Scholar

Summary

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

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