Skip to main content
Top

2021 | OriginalPaper | Chapter

Noise Robust Training of Segmentation Model Using Knowledge Distillation

Authors : Geetank Raipuria, Saikiran Bonthu, Nitin Singhal

Published in: Pattern Recognition. ICPR International Workshops and Challenges

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Deep Neural Networks are susceptible to label noise, which can lead to poor generalization. Degradation of labels in a Histopathology segmentation dataset can be especially caused due to the large inter-observer variability between expert annotators. Thus, obtaining a clean dataset may not be feasible. We address this by using Knowledge Distillation as a learned Label Smoothening Regularizer which has a denoising effect when training on a noisy dataset. To show the effectiveness of our approach, an evaluation is performed on the Gleason Challenge dataset which has high discordance between expert pathologists. Based on the reported experiments, we show that the distilled model achieves significant performance gain when training on the noisy dataset.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literature
1.
go back to reference Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization (2018) Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization (2018)
3.
go back to reference Lukasik, M., Bhojanapalli, S., Menon, A.K., Kumar, S.: Does label smoothing mitigate label noise? arXiv preprint arXiv:2003.02819 (2020) Lukasik, M., Bhojanapalli, S., Menon, A.K., Kumar, S.: Does label smoothing mitigate label noise? arXiv preprint arXiv:​2003.​02819 (2020)
4.
go back to reference Yuan, L., Tay, F.E.H., Li, G., Wang, T., Feng, J.: Revisiting knowledge distillation via label smoothing regularization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3903–3911 (2020) Yuan, L., Tay, F.E.H., Li, G., Wang, T., Feng, J.: Revisiting knowledge distillation via label smoothing regularization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3903–3911 (2020)
6.
go back to reference Ren, M., Zeng, W., Yang, B., Urtasun, R.: Learning to reweight examples for robust deep learning. arXiv preprint arXiv:1803.09050 (2018) Ren, M., Zeng, W., Yang, B., Urtasun, R.: Learning to reweight examples for robust deep learning. arXiv preprint arXiv:​1803.​09050 (2018)
7.
go back to reference Wang, Y., et al.: Iterative learning with open-set noisy labels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8688–8696 (2018) Wang, Y., et al.: Iterative learning with open-set noisy labels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8688–8696 (2018)
8.
go back to reference Jiang, L., Zhou, Z., Leung, T., Li, L.J., Fei-Fei, L.: Mentornet: learning data-driven curriculum for very deep neural networks on corrupted labels. In: International Conference on Machine Learning, pp. 2304–2313 (2018) Jiang, L., Zhou, Z., Leung, T., Li, L.J., Fei-Fei, L.: Mentornet: learning data-driven curriculum for very deep neural networks on corrupted labels. In: International Conference on Machine Learning, pp. 2304–2313 (2018)
9.
go back to reference Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in Neural Information Processing Systems, pp. 8527–8537 (2018) Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in Neural Information Processing Systems, pp. 8527–8537 (2018)
10.
go back to reference Li, Y., Yang, J., Song, Y., Cao, L., Luo, J., Li, L.J.: Learning from noisy labels with distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1910–1918 (2017) Li, Y., Yang, J., Song, Y., Cao, L., Luo, J., Li, L.J.: Learning from noisy labels with distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1910–1918 (2017)
11.
go back to reference Zhang, Z., Zhang, H., Arik, S.O., Lee, H., Pfister, T.: Distilling effective supervision from severe label noise. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9294–9303 (2020) Zhang, Z., Zhang, H., Arik, S.O., Lee, H., Pfister, T.: Distilling effective supervision from severe label noise. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9294–9303 (2020)
12.
go back to reference Ghosh, A., Kumar, H., Sastry, P.S.: Robust loss functions under label noise for deep neural networks. arXiv preprint arXiv:1712.09482 (2017) Ghosh, A., Kumar, H., Sastry, P.S.: Robust loss functions under label noise for deep neural networks. arXiv preprint arXiv:​1712.​09482 (2017)
13.
go back to reference Wang, X., Hua, Y., Kodirov, E., Robertson, N.M.: Imae for noise-robust learning: mean absolute error does not treat examples equally and gradient magnitude’s variance matters. arXiv preprint arXiv:1903.12141 (2019) Wang, X., Hua, Y., Kodirov, E., Robertson, N.M.: Imae for noise-robust learning: mean absolute error does not treat examples equally and gradient magnitude’s variance matters. arXiv preprint arXiv:​1903.​12141 (2019)
14.
go back to reference Wang, G., et al.: A noise-robust framework for automatic segmentation of covid-19 pneumonia lesions from CT images. IEEE Trans. Med. Imaging 39(8), 2653–2663 (2020)CrossRef Wang, G., et al.: A noise-robust framework for automatic segmentation of covid-19 pneumonia lesions from CT images. IEEE Trans. Med. Imaging 39(8), 2653–2663 (2020)CrossRef
16.
go back to reference Xie, J., Shuai, B., Hu, J.F., Lin, J., Zheng, W.S.: Improving fast segmentation with teacher-student learning. arXiv preprint arXiv:1810.08476 (2018) Xie, J., Shuai, B., Hu, J.F., Lin, J., Zheng, W.S.: Improving fast segmentation with teacher-student learning. arXiv preprint arXiv:​1810.​08476 (2018)
17.
go back to reference Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2604–2613 (2019) Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2604–2613 (2019)
18.
19.
go back to reference Gleason 2019 Challenge (2020). Accessed 10 Oct 2020 Gleason 2019 Challenge (2020). Accessed 10 Oct 2020
20.
go back to reference Nagpal, K., et al.: Development and validation of a deep learning algorithm for improving gleason scoring of prostate cancer. NPJ Dig. Med. 2(1), 1–10 (2019) Nagpal, K., et al.: Development and validation of a deep learning algorithm for improving gleason scoring of prostate cancer. NPJ Dig. Med. 2(1), 1–10 (2019)
21.
go back to reference Warfield, S.K., Zou, K.H., Wells, W.M.: Simultaneous truth and performance level estimation (staple): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging 23(7), 903–921 (2004) Warfield, S.K., Zou, K.H., Wells, W.M.: Simultaneous truth and performance level estimation (staple): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging 23(7), 903–921 (2004)
22.
go back to reference Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818 (2018) Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818 (2018)
23.
go back to reference He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
24.
go back to reference Nir, G., et al.: Automatic grading of prostate cancer in digitized histopathology images: Learning from multiple experts. Med. Image Anal. 50, 167–180 (2018) Nir, G., et al.: Automatic grading of prostate cancer in digitized histopathology images: Learning from multiple experts. Med. Image Anal. 50, 167–180 (2018)
Metadata
Title
Noise Robust Training of Segmentation Model Using Knowledge Distillation
Authors
Geetank Raipuria
Saikiran Bonthu
Nitin Singhal
Copyright Year
2021
DOI
https://doi.org/10.1007/978-3-030-68763-2_8

Premium Partner