Skip to main content

Meta-HRNet: A High Resolution Network for Coarse-to-Fine Few-Shot Classification

  • Conference paper
  • First Online:
Machine Learning and Knowledge Discovery in Databases: Research Track (ECML PKDD 2023)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14170))

  • 1366 Accesses

Abstract

Fine-grained classification has achieved success with the application of deep learning on large datasets. However, in practical scenarios, fine-grained categories often suffer from a lack of training data due to the difficulty of labeling. Leveraging accessible coarse-grained labeled data provides a promising way to alleviate this challenge, that is, the model learns from a large number of coarse-grained labeled data to perform better on fine-grained classification. In this paper, we focus on this coarse-to-fine few-shot problem and attribute the difficulty of this problem to two factors: the undistinguishable appearance of fine-grained images and the lack of fine-grained training samples. To address the first factor, we demonstrate that high-resolution features can capture more distinctive details that are useful for fine-grained classification tasks. Thus, we construct an improved high-resolution network called Meta-HRNet to capture rich details and filter the crucial detailed information for fine-grained classification. To address the second factor, we train the model by a two-step strategy that combines supervised training and episodic training. During the first training stage, the backbone of Meta-HRNet is optimized to obtain a basic ability of detailed representation. In the second stage, the attention module of the Meta-HRNet is trained to learn and sift key details given a low number of training samples. The effectiveness of our model is verified on four datasets. Experimental results demonstrate that the attention paid to the important details of images contributes to improving the performance of fine-grained classification tasks.

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

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/MadryLab/BREEDS-Benchmarks.

  2. 2.

    https://github.com/HRNet/HRNet-Image-Classification.

References

  1. Behera, A., Wharton, Z., Hewage, P.R.P.G., Bera, A.: Context-aware attentional pooling (cap) for fine-grained visual classification. Proc. AAAI Conf. Artif. Intell. 35(2), 929ā€“937 (2021)

    Google Scholar 

  2. Bukchin, G., et al.: Fine-grained angular contrastive learning with coarse labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8730ā€“8740 (2021)

    Google Scholar 

  3. Cantelli, F.P.: Sui confini della probabilitĆ”. In: Atti del Congresso Internazionale dei Matematici: Bologna del 3 al 10 de settembre di 1928, Vol. 6, 1929 (Comunicazioni, sezione IV (A)-V-VII), pp. 47ā€“60 (1929)

    Google Scholar 

  4. Chen, W., Si, C., Wang, W., Wang, L., Wang, Z., Tan, T.: Few-shot learning with part discovery and augmentation from unlabeled images. In: Zhou, Z.H. (ed.) Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pp. 2271ā€“2277. International Joint Conferences on Artificial Intelligence Organization (2021), main Track

    Google Scholar 

  5. Chen, X., Fan, H., Girshick, R.B., He, K.: Improved baselines with momentum contrastive learning. CoRR abs/2003.04297 (2020)

    Google Scholar 

  6. Chen, Y., Liu, Z., Xu, H., Darrell, T., Wang, X.: Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9042ā€“9051. IEEE, Montreal, QC, Canada (Oct 2021)

    Google Scholar 

  7. Cui, Y., Song, Y., Sun, C., Howard, A., Belongie, S.: Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4109ā€“4118. IEEE, Salt Lake City, UT, USA (Jun 2018)

    Google Scholar 

  8. Dong, B., Zhou, P., Yan, S., Zuo, W.: Self-promoted supervision for few-shot transformer. In: Avidan, S., Brostow, G., CissĆ©, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision (ECCV 2022), pp. 329ā€“347. Springer Nature Switzerland, Cham (2022)

    Chapter  Google Scholar 

  9. Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 1126ā€“1135. PMLR (06ā€“11 Aug 2017)

    Google Scholar 

  10. dan Guo, D., Tian, L., Zhao, H., Zhou, M., Zha, H.: Adaptive distribution calibration for few-shot learning with hierarchical optimal transport. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022)

    Google Scholar 

  11. Kao, C.H., Chiu, W.C., Chen, P.Y.: MAML is a noisy contrastive learner in classification. In: International Conference on Learning Representations (2022)

    Google Scholar 

  12. Kim, Y., Ha, J.W.: Contrastive fine-grained class clustering via generative adversarial networks (2022)

    Google Scholar 

  13. Lee, S., Moon, W., Heo, J.P.: Task discrepancy maximization for fine-grained few-shot classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5331ā€“5340 (June 2022)

    Google Scholar 

  14. Li, S., et al.: Improve unsupervised pretraining for few-label transfer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10201ā€“10210 (October 2021)

    Google Scholar 

  15. Luo, X., Xu, J., Xu, Z.: Channel importance matters in few-shot image classification. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 162, pp. 14542ā€“14559. PMLR (2022)

    Google Scholar 

  16. Ni, R., Shu, M., Souri, H., Goldblum, M., Goldstein, T.: The close relationship between contrastive learning and meta-learning. In: International Conference on Learning Representations (2022)

    Google Scholar 

  17. Oh, J., Kim, S., Ho, N., Kim, J.H., Song, H., Yun, S.Y.: Understanding cross-domain few-shot learning based on domain similarity and few-shot difficulty. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022)

    Google Scholar 

  18. Phoo, C.P., Hariharan, B.: Self-training for few-shot transfer across extreme task differences. In: International Conference on Learning Representations (2021)

    Google Scholar 

  19. Requeima, J., Gordon, J., Bronskill, J., Nowozin, S., Turner, R.E.: Fast and flexible multi-task classification using conditional neural adaptive processes. In: Advances in Neural Information Processing Systems. vol. 32. Curran Associates, Inc. (2019)

    Google Scholar 

  20. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234ā€“241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  21. Santurkar, S., Tsipras, D., Madry, A.: BREEDS: Benchmarks for subpopulation shift. In: International Conference on Learning Representations (2021)

    Google Scholar 

  22. Shen, Z., Liu, Z., Qin, J., Savvides, M., Cheng, K.T.: Partial is better than all: revisiting fine-tuning strategy for few-shot learning. Proc. AAAI Conf. Artif. Intell. 35(11), 9594ā€“9602 (2021)

    Google Scholar 

  23. Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. Adv. Neural Inform. Process. Syst. 30 (2017)

    Google Scholar 

  24. Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Analysis Mach. Intell. 43(10), 3349ā€“3364 (2021)

    Google Scholar 

  25. Yang, J., Yang, H., Chen, L.: Towards cross-granularity few-shot learning: coarse-to-fine pseudo-labeling with visual-semantic meta-embedding. In: Proceedings of the 29th ACM International Conference on Multimedia,pp. 3005ā€“3014. ACM, Virtual Event China (2021)

    Google Scholar 

  26. Yang, S., Liu, L., Xu, M.: Free lunch for few-shot learning: Distribution calibration. In: International Conference on Learning Representations (2021)

    Google Scholar 

  27. Ye, H.J., Hu, H., Zhan, D.C., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8808ā€“8817 (2020)

    Google Scholar 

  28. Zhao, B., Feng, J., Wu, X., Yan, S.: A survey on deep learning-based fine-grained object classification and semantic segmentation. Int. J. Autom. Comput. 14(2), 119ā€“135 (2017)

    Article  Google Scholar 

  29. Zhu, M., et al.: Dynamic resolution network. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Adv. Neural Inform. Process. Syst. 34, 27319ā€“21330 (2021)

    Google Scholar 

  30. Zhu, Y., Liu, C., Jiang, S.: Multi-attention Meta Learning for Few-shot Fine-grained Image Recognition. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, pp. 1090ā€“1096. International Joint Conferences on Artificial Intelligence Organization, Yokohama, Japan (Jul 2020)

    Google Scholar 

Download references

Acknowledgements

The authors are grateful to anonymous reviewers for their valuable comments. This work was partly supported by the National Natural Science Foundation of China under Grant No. 61572002, No. 61690201, and No. 61732001.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Zhaochen Li .

Editor information

Editors and Affiliations

Ethics declarations

Ethical Statement

This research does not contain any personally identifiable information. All datasets were obtained from public resources. The methods proposed in our paper do not have any potential negative societal impacts. Our methods are safe and cannot be integrated into weapons systems. Our research does not have the potential to damage human rights, economic security, peopleā€™s livelihoods, or the environment. This is a basic study and even if the methods are misused, they will not cause social harm.

Rights and permissions

Reprints and permissions

Copyright information

Ā© 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, Z., Mu, K. (2023). Meta-HRNet: A High Resolution Network for Coarse-to-Fine Few-Shot Classification. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14170. Springer, Cham. https://doi.org/10.1007/978-3-031-43415-0_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-43415-0_28

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-43414-3

  • Online ISBN: 978-3-031-43415-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics