Skip to main content

Coarse-To-Fine Incremental Few-Shot Learning

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13691))

Included in the following conference series:

Abstract

Different from fine-tuning models pre-trained on a large-scale dataset of preset classes, class-incremental learning (CIL) aims to recognize novel classes over time without forgetting pre-trained classes. However, a given model will be challenged by test images with finer-grained classes, e.g., a basenji is at most recognized as a dog. Such images form a new training set (i.e., support set) so that the incremental model is hoped to recognize a basenji (i.e., query) as a basenji next time. This paper formulates such a hybrid natural problem of coarse-to-fine few-shot (C2FS) recognition as a CIL problem named C2FSCIL, and proposes a simple, effective, and theoretically-sound strategy Knowe: to learn, freeze, and normalize a classifier’s weights from fine labels, once learning an embedding space contrastively from coarse labels. Besides, as CIL aims at a stability-plasticity balance, new overall performance metrics are proposed. In hat sense, on CIFAR-100, BREEDS, and tieredImageNet, Knowe outperforms all recent relevant CIL or FSCIL methods.

X. Xiang—Also with China’s Belt & Road Joint Lab on Measurement & Control Tech., and National Key Lab of S &T on Multispectral Info Processing.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /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
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

Notes

  1. 1.

    https://github.com/HAIV-Lab/Knowe.

References

  1. Abdelsalam, M., Faramarzi, M., Sodhani, S., Chandar, S.: IIRC: incremental implicitly-refined classification. In: CVPR (2021)

    Google Scholar 

  2. Akyürek, A.F., Akyürek, E., Wijaya, D., Andreas, J.: Subspace regularizers for few-shot class incremental learning. arxiv:2110.07059 (2021). (preprint)

  3. Belouadah, E., Popescu, A.: ScaIL: classifier weights scaling for class incremental learning. In: IEEE/CVF Winter Conference on Applications of Computer Vision (2020)

    Google Scholar 

  4. Belouadah, E., Popescu, A., Kanellos, I.: Initial classifier weights replay for memoryless class incremental learning. arXiv:2008.13710 (2020). (preprint)

  5. Bendale, A., Boult, T.: Towards open world recognition. In: CVPR (2015)

    Google Scholar 

  6. Bukchin, G., et al.: Fine-grained angular contrastive learning with coarse labels. In: CVPR (2021)

    Google Scholar 

  7. Cha, H., Lee, J., Shin, J.: Co2L: contrastive continual learning. In: ICCV (2021)

    Google Scholar 

  8. Delange, M., et al.: A continual learning survey: defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell. 44, 3366–3385 (2021)

    Google Scholar 

  9. Dhar, P., Singh, R.V., Peng, K.C., Wu, Z., Chellappa, R.: Learning without memorizing. In: CVPR (2019)

    Google Scholar 

  10. Dong, S., Hong, X., Tao, X., Chang, X., Wei, X.: Few-shot class-incremental learning via relation knowledge distillation. In: AAAI (2021)

    Google Scholar 

  11. Fotakis, D., Kalavasis, A., Kontonis, V., Tzamos, C.: Efficient algorithms for learning from coarse labels. In: 34th Annual Conference on Learning Theory (2021)

    Google Scholar 

  12. Geoffrey, H., Oriol, V., Jeff, D.: Distilling the knowledge in a neural network. In: NeurIPS (2015)

    Google Scholar 

  13. Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: CVPR (2018)

    Google Scholar 

  14. He, C., Wang, R., Chen, X.: A tale of two CILs: the connections between class incremental learning and class imbalanced learning, and beyond. In: CVPR Workshops (2021)

    Google Scholar 

  15. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)

    Google Scholar 

  16. Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Learning a unified classifier incrementally via rebalancing. In: CVPR (2019)

    Google Scholar 

  17. Hu, X., Tang, K., Miao, C., Hua, X.S., Zhang, H.: Distilling causal effect of data in class-incremental learning. In: CVPR (2021)

    Google Scholar 

  18. Hung, S.C.Y., Tu, C.H., Wu, C.E., Chen, C.H., Chan, Y.M., Chen, C.S.: Compacting, picking and growing for unforgetting continual learning. In: NeurIPS (2019)

    Google Scholar 

  19. Jung, S., Ahn, H., Cha, S., Moon, T.: Continual learning with node-importance based adaptive group sparse regularization. In: NeurIPS (2020)

    Google Scholar 

  20. Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)

    Article  MathSciNet  Google Scholar 

  21. Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report, Unvieristy of Toronto (2009)

    Google Scholar 

  22. Kukleva, A., Kuehne, H., Schiele, B.: Generalized and incremental few-shot learning by explicit learning and calibration without forgetting. In: ICCV (2021)

    Google Scholar 

  23. Kuzborskij, I., Orabona, F., Caputo, B.: From n to n+1: multiclass transfer incremental learning. In: CVPR (2013)

    Google Scholar 

  24. Lee, J., Hong, H.G., Joo, D., Kim, J.: Continual learning with extended Kronecker-factored approximate curvature. In: CVPR (2020)

    Google Scholar 

  25. Lee, S.W., Kim, J.H., Jun, J., Ha, J.W., Zhang, B.T.: Overcoming catastrophic forgetting by incremental moment matching. In: NIPS (2017)

    Google Scholar 

  26. Li, Z., Hoiem, D.: Learning without forgetting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 614–629. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_37

    Chapter  Google Scholar 

  27. Liu, C., et al.: Learning a few-shot embedding model with contrastive learning. In: AAAI (2021)

    Google Scholar 

  28. Liu, Y., Schiele, B., Sun, Q.: Adaptive aggregation networks for class-incremental learning. In: CVPR (2021)

    Google Scholar 

  29. Liu, Y., Su, Y., Liu, A.A., Schiele, B., Sun, Q.: Mnemonics training: multi-class incremental learning without forgetting. In: CVPR (2020)

    Google Scholar 

  30. Mai, Z., Li, R., Jeong, J., Quispe, D., Kim, H., Sanner, S.: Online continual learning in image classification: an empirical survey. arXiv:2101.10423 (2021). (preprint)

  31. Mallya, A., Davis, D., Lazebnik, S.: Piggyback: adapting a single network to multiple tasks by learning to mask weights. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 72–88. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_5

    Chapter  Google Scholar 

  32. Mallya, A., Lazebnik, S.: PackNet: adding multiple tasks to a single network by iterative pruning. In: CVPR (2018)

    Google Scholar 

  33. Masana, M., Liu, X., Twardowski, B., Menta, M., Bagdanov, A.D., van de Weijer, J.: Class-incremental learning: survey and performance evaluation on image classification. arXiv:2010.15277 (2020). (preprint)

  34. Mermillod, M., Bugaiska, A., Bonin, P.: The stability-plasticity dilemma: investigating the continuum from catastrophic forgetting to age-limited learning effects. Front. Psychol. 4, 504 (2013)

    Article  Google Scholar 

  35. French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3, 128–135 (1999)

    Article  Google Scholar 

  36. Pan, P., Swaroop, S., Immer, A., Eschenhagen, R., Turner, R.E., Khan, M.E.: Continual deep learning by functional regularisation of memorable past. In: NeurIPS (2020)

    Google Scholar 

  37. Qi, H., Brown, M., Lowe, D.G.: Low-shot learning with imprinted weights. In: CVPR (2018)

    Google Scholar 

  38. Rebuff, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: CVPR (2017)

    Google Scholar 

  39. Ren, M., Liao, R., Fetaya, E., Zemel, R.S.: Incremental few-shot learning with attention attractor networks. In: NeurIPS (2019)

    Google Scholar 

  40. Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. In: ICLR (2018)

    Google Scholar 

  41. Riemer, M., et al.: Learning to learn without forgetting by maximizing transfer and minimizing interference. In: ICLR (2019)

    Google Scholar 

  42. Ristin, M., Gall, J., Guillaumin, M., Gool, L.V.: From categories to subcategories: large-scale image classification with partial class label refinement. In: CVPR (2015)

    Google Scholar 

  43. Ristin, M., Guillaumin, M., Gall, J., Gool, L.V.: Incremental learning of NCM forests for large-scale image classification. In: CVPR (2014)

    Google Scholar 

  44. Santurkar, S., Tsipras, D., Madry, A.: Breeds: Benchmarks for subpopulation shift arXiv:2008.04859 (2020). (preprint)

  45. Shi, Y., Yuan, L., Chen, Y., Feng, J.: Continual learning via bit-level information preserving. In: CVPR (2021)

    Google Scholar 

  46. Singh, P., Mazumder, P., Rai, P., Namboodiri, V.P.: Rectification-based knowledge retention for continual learning. In: CVPR (2021)

    Google Scholar 

  47. Singh, P., Verma, V.K., Mazumder, P., Carin, L., Rai, P.: Calibrating CNNs for lifelong learning. In: NeurIPS (2020)

    Google Scholar 

  48. Tao, X., Chang, X., Hong, X., Wei, X., Gong, Y.: Topology-preserving class-incremental learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 254–270. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58529-7_16

    Chapter  Google Scholar 

  49. Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., Gong, Y.: Few-shot class-incremental learning. In: CVPR (2020)

    Google Scholar 

  50. Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., Isola, P.: Rethinking few-shot image classification: a good embedding is all you need? In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 266–282. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_16

    Chapter  Google Scholar 

  51. Wang, F., Xiang, X., Cheng, J., Yuille, A.L.: NormFace: L2 hypersphere embedding for face verification. In: ACM Conference on Multimedia (2017)

    Google Scholar 

  52. Wang, S., Li, X., Sun, J., Xu, Z.: Training networks in null space of feature covariance for continual learning. In: CVPR (2021)

    Google Scholar 

  53. Wu, G., Gong, S., Li, P.: Striking a balance between stability and plasticity for class-incremental learning. In: ICCV (2021)

    Google Scholar 

  54. Xu, Y., Qian, Q., Li, H., Jin, R., Hu, J.: Weakly supervised representation learning with coarse labels. In: ICCV (2021)

    Google Scholar 

  55. Yang, J., Yang, H., Chen, L.: Towards cross-granularity few-shot learning: coarse-to-fine pseudo-labeling with visual-semantic meta-embedding. In: ACM Conference on Multimedia (2021)

    Google Scholar 

  56. Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., Xu, Y.: Few-shot incremental learning with continually evolved classifiers. In: CVPR (2021)

    Google Scholar 

  57. Zhao, B., Xiao, X., Gan, G., Zhang, B., Xia, S.: Maintaining discrimination and fairness in class incremental learning. In: CVPR (2020)

    Google Scholar 

  58. Zhu, F., Zhang, X.Y., Wang, C., Yin, F., Liu, C.L.: Prototype augmentation and self-supervision for incremental learning. In: CVPR (2021)

    Google Scholar 

Download references

Acknowledgement

This research was supported by National NSFC (62176100), National Key R &D Program of China (2021ZD0201300), HUST Independent Innovation Res. Fund (2021XXJS096), Sichuan Univ. Interdisciplinary Innovation Res. Fund (RD-03-202108), and MoE Key Lab of Image Processing & Inteliigent Control

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Xiang Xiang .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2661 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

Xiang, X., Tan, Y., Wan, Q., Ma, J., Yuille, A., Hager, G.D. (2022). Coarse-To-Fine Incremental Few-Shot Learning. 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 13691. Springer, Cham. https://doi.org/10.1007/978-3-031-19821-2_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19821-2_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19820-5

  • Online ISBN: 978-3-031-19821-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics