Skip to main content

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

Unlike the conventional Knowledge Distillation (KD), Self-KD allows a network to learn knowledge from itself without any guidance from extra networks. This paper proposes to perform Self-KD from image Mixture (MixSKD), which integrates these two techniques into a unified framework. MixSKD mutually distills feature maps and probability distributions between the random pair of original images and their mixup images in a meaningful way. Therefore, it guides the network to learn cross-image knowledge by modelling supervisory signals from mixup images. Moreover, we construct a self-teacher network by aggregating multi-stage feature maps for providing soft labels to supervise the backbone classifier, further improving the efficacy of self-boosting. Experiments on image classification and transfer learning to object detection and semantic segmentation demonstrate that MixSKD outperforms other state-of-the-art Self-KD and data augmentation methods. The code is available at https://github.com/winycg/Self-KD-Lib.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: CVPR, pp. 1209–1218 (2018)

    Google Scholar 

  2. Cai, Z., Vasconcelos, N.: Cascade r-CNN: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483–1498 (2019)

    Article  Google Scholar 

  3. Chen, D., Mei, J.P., Wang, C., Feng, Y., Chen, C.: Online knowledge distillation with diverse peers. In: AAAI, pp. 3430–3437 (2020)

    Google Scholar 

  4. Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)

  5. Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)

  6. Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 113–123 (2019)

    Google Scholar 

  7. Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: CVPR Workshops, pp. 702–703 (2020)

    Google Scholar 

  8. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)

    Google Scholar 

  9. DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)

  10. Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)

    Article  Google Scholar 

  11. Ge, S., Luo, Z., Zhang, C., Hua, Y., Tao, D.: Distilling channels for efficient deep tracking. IEEE Trans. Image Process. 29, 2610–2621 (2019)

    Article  MATH  Google Scholar 

  12. Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)

    Google Scholar 

  13. Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICLR (2015)

    Google Scholar 

  14. 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)

    Google Scholar 

  15. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)

  16. Hou, Y., Ma, Z., Liu, C., Loy, C.C.: Learning lightweight lane detection CNNs by self attention distillation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1013–1021 (2019)

    Google Scholar 

  17. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 4700–4708 (2017)

    Google Scholar 

  18. Ji, M., Shin, S., Hwang, S., Park, G., Moon, I.C.: Refine myself by teaching myself: feature refinement via self-knowledge distillation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10664–10673 (2021)

    Google Scholar 

  19. Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: Stanford dogs. In: Proceedings of CVPR Workshop on Fine-Grained Visual Categorization (FGVC), vol. 2. Citeseer (2011)

    Google Scholar 

  20. Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: ICCV Workshops, pp. 554–561 (2013)

    Google Scholar 

  21. Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report (2009)

    Google Scholar 

  22. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  23. Liu, J., Qin, H., Wu, Y., Guo, J., Liang, D., Xu, K.: CoupleFace: relation matters for face recognition distillation. In: Proceedings of the European Conference on Computer Vision (2022)

    Google Scholar 

  24. Liu, J., Yu, T., Peng, H., Sun, M., Li, P.: Cross-lingual cross-modal consolidation for effective multilingual video corpus moment retrieval. In: NAACL-HLT (2022)

    Google Scholar 

  25. Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)

  26. Miyato, T., Maeda, S.i., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1979–1993 (2018)

    Google Scholar 

  27. Peng, B., et al.: Correlation congruence for knowledge distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5007–5016 (2019)

    Google Scholar 

  28. Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 413–420. IEEE (2009)

    Google Scholar 

  29. Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2016)

    Article  Google Scholar 

  30. Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: ICLR (2015)

    Google Scholar 

  31. Sun, D., Yao, A., Zhou, A., Zhao, H.: Deeply-supervised knowledge synergy. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6997–7006 (2019)

    Google Scholar 

  32. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)

    Google Scholar 

  33. Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states. In: International Conference on Machine Learning, pp. 6438–6447. PMLR (2019)

    Google Scholar 

  34. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset. Technical report (2011)

    Google Scholar 

  35. Wang, D., Li, Y., Wang, L., Gong, B.: Neural networks are more productive teachers than human raters: active mixup for data-efficient knowledge distillation from a blackbox model. In: CVPR, pp. 1498–1507 (2020)

    Google Scholar 

  36. Wang, Y., Xu, C., Xu, C., Tao, D.: Adversarial learning of portable student networks. In: AAAI, vol. 32 (2018)

    Google Scholar 

  37. Xu, T.B., Liu, C.L.: Data-distortion guided self-distillation for deep neural networks. In: AAAI, vol. 33, pp. 5565–5572 (2019)

    Google Scholar 

  38. Yang, C., An, Z., Cai, L., Xu, Y.: Hierarchical self-supervised augmented knowledge distillation. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, pp. 1217–1223 (2021)

    Google Scholar 

  39. Yang, C., An, Z., Cai, L., Xu, Y.: Knowledge distillation using hierarchical self-supervision augmented distribution. IEEE Trans. Neural Netw. Learn. Syst. (2022)

    Google Scholar 

  40. Yang, C., An, Z., Cai, L., Xu, Y.: Mutual contrastive learning for visual representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 3045–3053 (2022)

    Google Scholar 

  41. Yang, C., An, Z., Xu, Y.: Multi-view contrastive learning for online knowledge distillation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3750–3754 (2021)

    Google Scholar 

  42. Yang, C., ET AL.: Gated convolutional networks with hybrid connectivity for image classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12581–12588 (2020)

    Google Scholar 

  43. Yang, C., Zhou, H., An, Z., Jiang, X., Xu, Y., Zhang, Q.: Cross-image relational knowledge distillation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12319–12328 (2022)

    Google Scholar 

  44. Yang, D., et al.: Multi-view correlation distillation for incremental object detection. Pattern Recogn. 131, 108863 (2022)

    Article  Google Scholar 

  45. Yang, Z., Li, Z., Jiang, X., Gong, Y., Yuan, Z., Zhao, D., Yuan, C.: Focal and global knowledge distillation for detectors. In: CVPR, pp. 4643–4652 (2022)

    Google Scholar 

  46. Yuan, L., Tay, F.E., 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)

    Google Scholar 

  47. Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6023–6032 (2019)

    Google Scholar 

  48. Yun, S., Park, J., Lee, K., Shin, J.: Regularizing class-wise predictions via self-knowledge distillation. In: CVPR, pp. 13876–13885 (2020)

    Google Scholar 

  49. Zagoruyko, S., Komodakis, N.: Wide residual networks. In: Proceedings of the British Machine Vision Conference (2016)

    Google Scholar 

  50. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: ICLR (2018)

    Google Scholar 

  51. Zhang, L., Bao, C., Ma, K.: Self-distillation: towards efficient and compact neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 44, 4388–4403 (2021)

    Google Scholar 

  52. Zhang, L., Song, J., Gao, A., Chen, J., Bao, C., Ma, K.: Be your own teacher: improve the performance of convolutional neural networks via self distillation. In: ICCV, pp. 3713–3722 (2019)

    Google Scholar 

  53. Zhang, L., Yu, M., Chen, T., Shi, Z., Bao, C., Ma, K.: Auxiliary training: towards accurate and robust models. In: CVPR, pp. 372–381 (2020)

    Google Scholar 

  54. Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4320–4328 (2018)

    Google Scholar 

  55. Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: AAAI. vol. 34, pp. 13001–13008 (2020)

    Google Scholar 

  56. Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR. pp. 633–641 (2017)

    Google Scholar 

  57. Zhu, X., Gong, S., et al.: Knowledge distillation by on-the-fly native ensemble. In: Advances in Neural Information Processing Systems, pp. 7517–7527 (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Zhulin An .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 325 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Yang, C. et al. (2022). MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13684. Springer, Cham. https://doi.org/10.1007/978-3-031-20053-3_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20053-3_31

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20052-6

  • Online ISBN: 978-3-031-20053-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics