Skip to main content
SpringerLink
Log in

Decoupled Learning for Long-Tailed Oracle Character Recognition

  • Conference paper
  • First Online:
Document Analysis and Recognition - ICDAR 2023 (ICDAR 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14190))

Included in the following conference series:

  • 635 Accesses

Abstract

Oracle character recognition has recently made significant progress with the success of deep neural networks (DNNs), but it is far from being solved. Most works do not consider the long-tailed distribution issue in oracle character recognition, resulting in a biased DNN towards head classes. To overcome this issue, we propose a two-stage decoupled learning method to train an unbiased DNN model for long-tailed oracle character recognition. In the first stage, we optimize the DNN under instance-balanced sampling, obtaining a robust backbone but biased classifier. In the second stage, we propose two strategies to refine the classifier under class-balanced sampling. Specifically, we add a learnable weight scaling module which can adjust the classifier to respect tail classes; meanwhile, we integrate the KL-divergence loss to maintain attention to head classes through knowledge distillation from the first stage. Coupling these two designs enables us to train an unbiased DNN model in oracle character recognition. Our proposed method achieves new state-of-the-art performance on three benchmark datasets, including OBC306, Oracle-AYNU and Oracle-20K.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 99.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 129.99
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

Notes

  1. 1.

    We divide the oracle data into three categories: the classes with many samples as head classes, the classes with few samples as tail classes, and the remainder are the medium classes described in Sect. 4.3.

References

  1. Guo, J., Wang, C., Roman-Rangel, E., et al.: Building hierarchical representations for oracle character and sketch recognition. IEEE Trans. Image Process. 1, 104–118 (2016)

    Article  MathSciNet  MATH  Google Scholar 

  2. Huang, S., Wang, H., Liu, Y., et al.: OBC306: a large-scale oracle bone character recognition dataset. In: Proceedings of International Conference on Document Analysis and Recognition (ICDAR), pp. 681–688 (2019)

    Google Scholar 

  3. Zhang, Y.-K., Zhang, H., Liu, Y.-G., et al.: Oracle character recognition by nearest neighbor classification with deep metric learning. In: Proceedings of International Conference on Document Analysis and Recognition (ICDAR), pp. 309–314 (2019)

    Google Scholar 

  4. Huang, K., Hussain, A., Wang, Q.-F., Zhang, R.: Deep Learning: Fundamentals, Theory and Applications, vol. 2 (2019)

    Google Scholar 

  5. Li, J., Wang, Q.-F., Zhang, R., Huang, K.: Mix-up augmentation for oracle character recognition with imbalanced data distribution. In: Proceedings of International Conference on Document Analysis and Recognition (ICDAR), pp. 237–251 (2021)

    Google Scholar 

  6. Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)

    Article  MATH  Google Scholar 

  7. Estabrooks, A., Jo, T., Japkowicz, N.: A multiple resampling method for learning from imbalanced data sets. Comput. Intell. 20(1), 18–36 (2004)

    Article  MathSciNet  Google Scholar 

  8. Cui, Y., Jia, M., Lin, T.-Y., et al.: Class-balanced loss based on effective number of samples. In: Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9268–9277 (2019)

    Google Scholar 

  9. Cao, K., Wei, C., Gaidon, A., et al.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), pp. 1565–1576 (2019)

    Google Scholar 

  10. Menon, A.K., Jayasumana, S., Rawat, A.S., et al.: Long-tail learning via logit adjustment. In: Proceedings of International Conference on Learning Representations (ICLR) (2021)

    Google Scholar 

  11. Wu, T., Liu, Z., Huang, Q., et al.: Adversarial robustness under long-tailed distribution. In: Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8659–8668 (2021)

    Google Scholar 

  12. Kang, B., Xie, S., Rohrbach,, M., et al.: Decoupling representation and classifier for long-tailed recognition. In: Proceedings of International Conference on Learning Representations (ICLR) (2020)

    Google Scholar 

  13. Kang, B., Li, Y., Xie, S., et al.: Exploring balanced feature spaces for representation learning. In: Proceedings of International Conference on Learning Representations (ICLR) (2021)

    Google Scholar 

  14. Zhong, Z., Cui, J., Liu, S., Jia, J.: Improving calibration for long-tailed recognition. In: Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16489–16498 (2021)

    Google Scholar 

  15. Alshammari, S., Wang, Y.-X., Ramanan, D., Kong S.: Long-tailed recognition via weight balancing. In: Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6887–6897 (2022)

    Google Scholar 

  16. Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations (ICLR) (2021)

    Google Scholar 

  17. Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: Proceedings of International Conference on Learning Representations (ICLR) (2018)

    Google Scholar 

  18. Li, Q., Yang, Y., Wang, A.: Recognition of inscriptions on bones or tortoise shells based on graph isomorphism. Jisuanji Gongcheng yu Yingyong (Comput. Eng. Appl.) 47(8), 112–114 (2011)

    Google Scholar 

  19. Liu, Y., Liu, G.: Oracle bone inscription recognition based on SVM. J. Anyang Normal Univ. 2, 54–56 (2017)

    Google Scholar 

  20. Wang, X., Lian, L., Miao, Z., et al.: Long-tailed recognition by routing diverse distribution-aware experts. In: Proceedings of International Conference on Learning Representations (ICLR) (2021)

    Google Scholar 

  21. Zhang, Y., Hooi, B., Hong, L., Feng, J.: Self-supervised aggregation of diverse experts for test-agnostic long-tailed recognition. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)

    Google Scholar 

  22. Gou, J., Baosheng, Yu., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vision 129(6), 1789–1819 (2021)

    Article  Google Scholar 

  23. Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015)

    Google Scholar 

  24. Xiang, L., Ding, G., Han, J.: Learning from multiple experts: self-paced knowledge distillation for long-tailed classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 247–263. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_15

    Chapter  Google Scholar 

  25. Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 4171–4186 (2019)

    Google Scholar 

  26. He, K., Chen, X., Xie, S., et al.: Masked autoencoders are scalable vision learners. In: Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15979–15988 (2022)

    Google Scholar 

  27. Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), pp. 5998–6008 (2017)

    Google Scholar 

  28. Verma, V., Lamb, A., Beckham, C., et al.: Manifold mixup: better representations by interpolating hidden states. In: Proceedings of International Conference on Machine Learning (ICML), pp. 6438–6447 (2019)

    Google Scholar 

  29. Yun, S., Han, D., Chun, S., et al.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of International Conference on Computer Vision (ICCV), pp. 6022–6031 (2019)

    Google Scholar 

  30. Zhang, Y., Wei, X.-S., Zhou, B., Wu, J.: Bag of tricks for long-tailed visual recognition with deep convolutional neural networks. In: Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), pp. 3447–3455 (2021)

    Google Scholar 

Download references

Acknowledgements

This research was funded by National Natural Science Foundation of China (NSFC) no.62276258, Jiangsu Science and Technology Programme (Natural Science Foundation of Jiangsu Province) no. BE2020006-4, and Xi’an Jiaotong-Liverpool University’s Key Program Special Fund no. KSF-T-06.

Author information

Authors and Affiliations

  1. School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China

    Jing Li & Qiu-Feng Wang

  2. Ricoh Software Research Center(Beijing) Co., Ltd., Beijing, China

    Bin Dong & Lei Ding

  3. School of Mathematics and Physics, Xi’an Jiaotong-Liverpool University, Suzhou, China

    Rui Zhang

  4. Data Science Research Center, Duke Kunshan University, Suzhou, China

    Kaizhu Huang

Authors
  1. Jing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bin Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qiu-Feng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lei Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Rui Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kaizhu Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qiu-Feng Wang .

Editor information

Editors and Affiliations

  1. TU Dortmund University, Dortmund, Germany

    Gernot A. Fink

  2. Adobe, College Park, MN, USA

    Rajiv Jain

  3. Osaka Metropolitan University, Osaka, Japan

    Koichi Kise

  4. Rochester Institute of Technology, Rochester, NY, USA

    Richard Zanibbi

Rights and permissions

Reprints and permissions

Copyright information

© 2023 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

Li, J., Dong, B., Wang, QF., Ding, L., Zhang, R., Huang, K. (2023). Decoupled Learning for Long-Tailed Oracle Character Recognition. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds) Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. Lecture Notes in Computer Science, vol 14190. Springer, Cham. https://doi.org/10.1007/978-3-031-41685-9_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-41685-9_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-41684-2

  • Online ISBN: 978-3-031-41685-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation