Abstract
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data set containing disjoint yet related categories. Apart from discovering novel classes, we also aim at preserving the ability of the model to recognize previously seen base categories. Inspired by rehearsal-based incremental learning methods, in this paper we propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes by jointly exploiting base class feature prototypes and feature-level knowledge distillation. We also propose a self-training clustering strategy that simultaneously clusters novel categories and trains a joint classifier for both the base and novel classes. This makes our method able to operate in a class-incremental setting. Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches. Code is available at https://github.com/OatmealLiu/class-iNCD.
S. Roy and M. Liu—Contributed equally.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
When referring to classes, we regard old & base; and, new & novel interchangeably.
References
Anderson, B.L.: Can computational goals inform theories of vision? Topics in Cognitive Science (2015)
Buzzega, P., Boschini, M., Porrello, A., Abati, D., Calderara, S.: Dark experience for general continual learning: a strong, simple baseline. In: NeurIPS (2020)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)
Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)
Castro, F.M., Marín-Jiménez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 241–257. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_15
Chaudhry, A., Dokania, P.K., Ajanthan, T., Torr, P.H.S.: Riemannian walk for incremental learning: understanding forgetting and intransigence. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 556–572. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_33
Chaudhry, A., et al.: Continual learning with tiny episodic memories. In: ICML (2019)
Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., Tuytelaars, T.: A continual learning survey: Defying forgetting in classification tasks. TPAMI (2021)
Dhar, P., Singh, R.V., Peng, K.C., Wu, Z., Chellappa, R.: Learning without memorizing. In: CVPR (2019)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)
Fini, E., Sangineto, E., Lathuilière, S., Zhong, Z., Nabi, M., Ricci, E.: A unified objective for novel class discovery. In: ICCV (2021)
French, R.M.: Catastrophic forgetting in connectionist networks. Trends in cognitive sciences (1999)
Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. In: ICLR (2014)
Han, K., Vedaldi, A., Zisserman, A.: Learning to discover novel visual categories via deep transfer clustering. In: ICCV (2019)
Han, K., Rebuffi, S.A., Ehrhardt, S., Vedaldi, A., Zisserman, A.: Automatically discovering and learning new visual categories with ranking statistics. In: ICLR (2020)
Han, K., Vedaldi, A., Zisserman, A.: Learning to discover novel visual categories via deep transfer clustering. In: ICCV (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hinton, G., Vinyals, O., Dean, J., et al.: Distilling the knowledge in a neural network. In: NeurIPS Workshop (2014)
Hsu, Y.C., Lv, Z., Kira, Z.: Learning to cluster in order to transfer across domains and tasks. In: ICLR (2018)
Hsu, Y.C., Lv, Z., Schlosser, J., Odom, P., Kira, Z.: Multi-class classification without multi-class labels. In: ICLR (2019)
Jia, X., Han, K., Zhu, Y., Green, B.: Joint representation learning and novel category discovery on single-and multi-modal data. In: ICCV (2021)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. In: NAS (2017)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. University of Tronto (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NeurIPS (2012)
Kuhn, H.W.: The hungarian method for the assignment problem. Naval research logistics quarterly (1955)
Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N (2015)
Li, Z., Hoiem, D.: Learning without forgetting. TPAMI (2017)
Liang, J., Hu, D., Feng, J.: Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In: ICML (2020)
Liu, Y., Tuytelaars, T.: Residual tuning: Toward novel category discovery without labels. TNNLS (2022)
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 preprint arXiv:2010.15277 (2020)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: icarl: Incremental classifier and representation learning. In: CVPR (2017)
Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., Fu, Y.: Large scale incremental learning. In: CVPR (2019)
Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: ICML (2016)
Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: ICML (2017)
Zhao, Y., Zhong, Z., Sebe, N., Lee, G.H.: Novel class discovery in semantic segmentation. In: CVPR (2022)
Zheng, Z., Yang, Y.: Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. IJCV (2021)
Zhong, Z., Fini, E., Roy, S., Luo, Z., Ricci, E., Sebe, N.: Neighborhood contrastive learning for novel class discovery. In: CVPR (2021)
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. In: CVPR (2021)
Acknowledgement
We thank the funding agencies: EU H2020 projects SPRING (No. 871245) and AI4 Media (No. 951911); and the EUREGIO project OLIVER.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Roy, S., Liu, M., Zhong, Z., Sebe, N., Ricci, E. (2022). Class-Incremental Novel Class Discovery. 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 13693. Springer, Cham. https://doi.org/10.1007/978-3-031-19827-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-19827-4_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19826-7
Online ISBN: 978-3-031-19827-4
eBook Packages: Computer ScienceComputer Science (R0)