Skip to main content
Springer Nature Link
Log in

Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15069))

Included in the following conference series:

  • 335 Accesses

Abstract

Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to prevent forgetting the old knowledge. However, this strategy restricts the model’s ability to adapt and effectively distinguish new categories. To address this, we introduce a novel technique integrating a learnable projector with feature distillation, thus enhancing model adaptability without sacrificing past knowledge. The resulting distribution shift of the previously learned categories is mitigated with the auxiliary category adaptation network. We demonstrate that while each component offers modest benefits individually, their combination – dubbed CAMP (Category Adaptation Meets Projected distillation) – significantly improves the balance between learning new information and retaining old. CAMP exhibits superior performance across several GCCD and Class Incremental Learning scenarios. The code is available on Github.

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

Access this chapter

Log in via an institution

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

References

  1. Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: ECCV (2018)

    Google Scholar 

  2. Arthur, D., Vassilvitskii, S.: K-means++ the advantages of careful seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1027–1035 (2007)

    Google Scholar 

  3. Bordes, F., Balestriero, R., Garrido, Q., Bardes, A., Vincent, P.: Guillotine regularization: why removing layers is needed to improve generalization in self-supervised learning. Trans. Mach. Learn. Res. (2023)

    Google Scholar 

  4. Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  5. Chaudhry, A., Dokania, P.K., Ajanthan, T., Torr, P.H.: Riemannian walk for incremental learning: understanding forgetting and intransigence. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 532–547 (2018)

    Google Scholar 

  6. Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations (2020)

    Google Scholar 

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

    Google Scholar 

  8. Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 6 words: transformers for image recognition at scale. ICLR (2021)

    Google Scholar 

  9. Douillard, A., Cord, M., Ollion, C., Robert, T., Valle, E.: PODNet: pooled outputs distillation for small-tasks incremental learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 86–102. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_6

    Chapter  Google Scholar 

  10. Fini, E., da Costa, V.G.T., Alameda-Pineda, X., Ricci, E., Alahari, K., Mairal, J.: Self-supervised models are continual learners. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18–24 June 2022, pp. 9611–9620. IEEE (2022)

    Google Scholar 

  11. Fini, E., Sangineto, E., Lathuilière, S., Zhong, Z., Nabi, M., Ricci, E.: A unified objective for novel class discovery. In: ICCV (2021)

    Google Scholar 

  12. French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3(4), 128–135 (1999)

    Article  Google Scholar 

  13. Gomez-Villa, A., Twardowski, B., Yu, L., Bagdanov, A.D., van de Weijer, J.: Continually learning self-supervised representations with projected functional regularization (2022)

    Google Scholar 

  14. Han, K., Rebuffi, S.A., Ehrhardt, S., Vedaldi, A., Zisserman, A.: Automatically discovering and learning new visual categories with ranking statistics (2020)

    Google Scholar 

  15. Han, K., Rebuffi, S., Ehrhardt, S., Vedaldi, A., Zisserman, A.: Autonovel: Automatically discovering and learning novel visual categories. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 6767–6781 (2022)

    Article  Google Scholar 

  16. Han, K., Vedaldi, A., Zisserman, A.: Learning to discover novel visual categories via deep transfer clustering. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8401–8409 (2019)

    Google Scholar 

  17. Iscen, A., Zhang, J., Lazebnik, S., Schmid, C.: Memory-efficient incremental learning through feature adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 699–715. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_41

    Chapter  Google Scholar 

  18. Joseph, K.J., et al.: Novel class discovery without forgetting. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. ECCV 2022. LNCS, vol. 13684, pp. 570–586. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20053-3_33

  19. Khosla, P., et al.: Supervised contrastive learning (2021)

    Google Scholar 

  20. Kim, H., Suh, S., Kim, D., Jeong, D., Cho, H., Kim, J.: Proxy anchor-based unsupervised learning for continuous generalized category discovery. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 16688–16697 (2023)

    Google Scholar 

  21. Kim, S., Kim, D., Cho, M., Kwak, S.: Proxy anchor loss for deep metric learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3238–3247 (2020)

    Google Scholar 

  22. Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)

    Article  MathSciNet  Google Scholar 

  23. Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: 2013 IEEE International Conference on Computer Vision Workshops, pp. 554–561 (2013)

    Google Scholar 

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

    Google Scholar 

  25. Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2017)

    Article  Google Scholar 

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

  27. 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. IEEE Trans. Pattern Anal. Mach. Intell. (2022)

    Google Scholar 

  28. Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1406–1415 (2019)

    Google Scholar 

  29. Petit, G., Popescu, A., Schindler, H., Picard, D., Delezoide, B.: Fetril: feature translation for exemplar-free class-incremental learning. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3911–3920 (2023)

    Google Scholar 

  30. Riemer, M., et al.: Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910 (2018)

  31. Roy, S., Liu, M., Zhong, Z., Sebe, N., Ricci, E.: Class-incremental novel class discovery. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. ECCV 2022. LNCS, vol. 13693, pp. 317–333. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19827-4_19

  32. Rypeść, G., Cygert, S., Khan, V., Trzciński, T., Zieliński, B., Twardowski, B.: Divide and not forget: ensemble of selectively trained experts in continual learning. arXiv preprint arXiv:2401.10191 (2024)

  33. Sariyildiz, M.B., Kalantidis, Y., Alahari, K., Larlus, D.: No reason for no supervision: Improved generalization in supervised models. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1–5 May 2023. OpenReview.net (2023)

    Google Scholar 

  34. Sariyildiz, M.B., Kalantidis, Y., Alahari, K., Larlus, D.: No reason for no supervision: improved generalization in supervised models. In: ICLR 2023-International Conference on Learning Representations, pp. 1–26 (2023)

    Google Scholar 

  35. Vaze, S., Han, K., Vedaldi, A., Zisserman, A.: Generalized category discovery. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7492–7501 (2022)

    Google Scholar 

  36. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)

    Google Scholar 

  37. Wen, X., Zhao, B., Qi, X.: Parametric classification for generalized category discovery: a baseline study. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 16590–16600 (2023)

    Google Scholar 

  38. Wu, Y., Chi, Z., Wang, Y., Feng, S.: Metagcd: learning to continually learn in generalized category discovery. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1655–1665 (2023)

    Google Scholar 

  39. Wu, Y., et al.: Large scale incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 374–382 (2019)

    Google Scholar 

  40. Yan, S., Xie, J., He, X.: Der: dynamically expandable representation for class incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3014–3023 (2021)

    Google Scholar 

  41. Yu, L., et al.: Semantic drift compensation for class-incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6982–6991 (2020)

    Google Scholar 

  42. Zhang, S., Khan, S., Shen, Z., Naseer, M., Chen, G., Khan, F.S.: Promptcal: contrastive affinity learning via auxiliary prompts for generalized novel category discovery. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3479–3488 (2023)

    Google Scholar 

  43. Zhang, X., et al.: Grow and merge: a unified framework for continuous categories discovery. Adv. Neural. Inf. Process. Syst. 35, 27455–27468 (2022)

    Google Scholar 

  44. Zhao, B., Mac Aodha, O.: Incremental generalized category discovery. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 19137–19147 (2023)

    Google Scholar 

  45. Zhao, B., Wen, X., Han, K.: Learning semi-supervised gaussian mixture models for generalized category discovery. arXiv preprint arXiv:2305.06144 (2023)

  46. Zhong, Z., Fini, E., Roy, S., Luo, Z., Ricci, E., Sebe, N.: Neighborhood contrastive learning for novel class discovery. In: CVPR (2021)

    Google Scholar 

  47. Zhong, Z., Zhu, L., Luo, Z., Li, S., Yang, Y., Sebe, N.: Openmix: reviving known knowledge for discovering novel visual categories in an open world (2020)

    Google Scholar 

  48. Zhou, D.W., Wang, F.Y., Ye, H.J., Zhan, D.C.: Pycil: a python toolbox for class-incremental learning. Sci. China Inf. Sci. 66(9), 197101– (2023)

    Google Scholar 

  49. Zhu, F., Cheng, Z., Zhang, X.Y., Liu, C.L.: Class-incremental learning via dual augmentation. Adv. Neural Inf. Process. Syst. 34 (2021)

    Google Scholar 

  50. Zhu, F., Zhang, X.Y., Wang, C., Yin, F., Liu, C.L.: Prototype augmentation and self-supervision for incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5871–5880 (2021)

    Google Scholar 

  51. Zhu, K., Zhai, W., Cao, Y., Luo, J., Zha, Z.J.: Self-sustaining representation expansion for non-exemplar class-incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9296–9305 (2022)

    Google Scholar 

Download references

Acknowledgments

Daniel Marczak is supported by National Centre of Science (NCN, Poland) Grant No. 2021/43/O/ST6/02482. This research was partially funded by National Science Centre, Poland, grant no: 2020/39/B/ST6/01511, 2022/45/B/ST6/02817, and 2023/51/D/ST6/02846. Bartłomiej Twardowski acknowledges the grant RYC2021-032765-I. This paper has been supported by the Horizon Europe Programme (HORIZON-CL4-2022-HUMAN-02) under the project “ELIAS: European Lighthouse of AI for Sustainability”, GA no. 101120237. We gratefully acknowledge Polish high-performance computing infrastructure PLGrid (HPC Center: ACK Cyfronet AGH) for providing computer facilities and support within computational grant no. PLG/2023/016613.

Author information

Authors and Affiliations

  1. IDEAS NCBR, Warsaw, Poland

    Grzegorz Rypeść, Daniel Marczak, Sebastian Cygert, Tomasz Trzciński & Bartłomiej Twardowski

  2. Warsaw University of Technology, Warsaw, Poland

    Grzegorz Rypeść, Daniel Marczak & Tomasz Trzciński

  3. Gdańsk University of Technology, Gdańsk, Poland

    Sebastian Cygert

  4. Tooploox, Warsaw, Poland

    Tomasz Trzciński

  5. Autonomous University of Barcelona, Bellaterra, Spain

    Bartłomiej Twardowski

  6. Computer Vision Center, Warsaw, Poland

    Bartłomiej Twardowski

Authors
  1. Grzegorz Rypeść
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Daniel Marczak
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sebastian Cygert
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tomasz Trzciński
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bartłomiej Twardowski
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Grzegorz Rypeść .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 3489 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 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

Rypeść, G., Marczak, D., Cygert, S., Trzciński, T., Twardowski, B. (2025). Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15069. Springer, Cham. https://doi.org/10.1007/978-3-031-73247-8_19

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-73247-8_19

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-73246-1

  • Online ISBN: 978-3-031-73247-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics