Abstract
To keep learning knowledge from a data stream with changing distribution, continual learning has attracted lots of interests recently. Among its various settings, online class-incremental learning (OCIL) is more realistic and challenging since the data can be used only once. Currently, by employing a buffer to store a few old samples, replay-based methods have obtained huge success and dominated this area. Due to the single pass property of OCIL, how to retrieve high-valued samples from memory is very important. In most of the current works, the logits from the last fully connected layer are used to estimate the value of samples. However, the imbalance between the number of samples for old and new classes leads to a severe bias of the FC layer, which results in an inaccurate estimation. Moreover, this bias also brings about abrupt feature change. To address this problem, we propose a dual supervised contrastive learning method based on perturbation uncertainty. Specifically, we retrieve samples that have not been learned adequately based on perturbation uncertainty. Retraining such samples helps the model to learn robust features. Then, we combine two types of supervised contrastive loss to replace the cross-entropy loss, which further enhances the feature robustness and alleviates abrupt feature changes. Extensive experiments on three popular datasets demonstrate that our method surpasses several recently published works.
S. Su and Z. Chen—Authors contributed equally.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ahn, H., Kwak, J., Lim, S., Bang, H., Kim, H., Moon, T.: Ss-il: separated softmax for incremental learning. In: ICCV, pp. 844–853 (2021)
Aljundi, R., et al.: Online continual learning with maximal interfered retrieval. Adv. Neural Inform. Process. Syst. 32 (2019)
Aljundi, R., Lin, M., Goujaud, B., Bengio, Y.: Gradient based sample selection for online continual learning. Adv. Neural Inform. Process. Syst. 32 (2019)
Bellitto, G., Pennisi, M., Palazzo, S., Bonicelli, L., Boschini, M., Calderara, S.: Effects of auxiliary knowledge on continual learning. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 1357–1363. IEEE (2022)
Boschini, M., Bonicelli, L., Buzzega, P., Porrello, A., Calderara, S.: Class-incremental continual learning into the extended der-verse. IEEE Trans. Pattern Anal. Mach. Intell. 45(5), 5497–5512 (2022)
Buzzega, P., Boschini, M., Porrello, A., Abati, D., Calderara, S.: Dark experience for general continual learning: a strong, simple baseline. Adv. Neural. Inf. Process. Syst. 33, 15920–15930 (2020)
Buzzega, P., Boschini, M., Porrello, A., Calderara, S.: Rethinking experience replay: a bag of tricks for continual learning. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2180–2187. IEEE (2021)
Caccia, L., Aljundi, R., Asadi, N., Tuytelaars, T., Pineau, J., Belilovsky, E.: New insights on reducing abrupt representation change in online continual learning. arXiv preprint arXiv:2104.05025 (2021)
Cha, H., Lee, J., Shin, J.: Co2l: contrastive continual learning. In: ICCV, pp. 9516–9525 (October 2021)
Chaudhry, A., Ranzato, M., Rohrbach, M., Elhoseiny, M.: Efficient lifelong learning with a-gem. arXiv preprint arXiv:1812.00420 (2018)
Chaudhry, A., et al.: On tiny episodic memories in continual learning. arXiv preprint arXiv:1902.10486 (2019)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597–1607. PMLR (2020)
Davari, M., Asadi, N., Mudur, S., Aljundi, R., Belilovsky, E.: Probing representation forgetting in supervised and unsupervised continual learning. In: CVPR, pp. 16712–16721 (June 2022)
Fu, Z., Wang, Z., Xu, X., Li, D., Yang, H.: Knowledge aggregation networks for class incremental learning. Pattern Recogn. 137, 109310 (2023)
Gallardo, J., Hayes, T.L., Kanan, C.: Self-supervised training enhances online continual learning (2021). https://arxiv.org/abs/2103.14010
Gu, Y., Yang, X., Wei, K., Deng, C.: Not just selection, but exploration: online class-incremental continual learning via dual view consistency. In: CVPR, pp. 7442–7451 (2022)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR, vol. 2, pp. 1735–1742. IEEE (2006)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729–9738 (2020)
Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: ECCV, pp. 709–727. Springer (2022)
Khosla, P., et al.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661–18673 (2020)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Handbook Systemic Autoimmune Diseases 1(4) (2009)
Li, X., Wang, S., Sun, J., Xu, Z.: Memory efficient data-free distillation for continual learning. Pattern Recogn. 144, 109875 (2023)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2017)
Liang, G., Chen, Z., Chen, Z., Ji, S., Zhang, Y.: New insights on relieving task-recency bias for online class incremental learning. IEEE Trans. Circuits Syst. Video Technol. 34(5), 3451–3464 (2024)
Liu, X., Masana, M., Herranz, L., Van de Weijer, J., Lopez, A.M., Bagdanov, A.D.: Rotate your networks: Better weight consolidation and less catastrophic forgetting. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 2262–2268. IEEE (2018)
Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. Adv. Neural Inform. Process. Syst. 30 (2017)
Mai, Z., Li, R., Jeong, J., Quispe, D., Kim, H., Sanner, S.: Online continual learning in image classification: an empirical survey. Neurocomputing 469, 28–51 (2022)
Mai, Z., Li, R., Kim, H., Sanner, S.: Supervised contrastive replay: revisiting the nearest class mean classifier in online class-incremental continual learning. In: CVPR, pp. 3589–3599 (2021)
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. 45(5), 5513–5533 (2023)
McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol. 24, pp. 109–165. Elsevier (1989)
Shi, F., Wang, P., Shi, Z., Rui, Y.: Selecting useful knowledge from previous tasks for future learning in a single network. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9727–9732. IEEE (2021)
Shim, D., Mai, Z., Jeong, J., Sanner, S., Kim, H., Jang, J.: Online class-incremental continual learning with adversarial shapley value. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 9630–9638 (2021)
Song, K., Liang, G., Chen, Z., Zhang, Y.: Non-exemplar class-incremental learning by random auxiliary classes augmentation and mixed features. IEEE Trans. Circ. Syst. Video Technol. (2024)
Van de Ven, G.M., Tuytelaars, T., Tolias, A.S.: Three types of incremental learning. Nat. Mach. Intell. 4(12), 1185–1197 (2022)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. Adv. Neural Inform. Process. Syst. 29 (2016)
Vitter, J.S.: Random sampling with a reservoir. ACM Trans. Math. Softw. (TOMS) 11(1), 37–57 (1985)
Wang, Q., Wang, R., Wu, Y., Jia, X., Meng, D.: Cba: improving online continual learning via continual bias adaptor. In: ICCV, pp. 19082–19092 (2023)
Wang, R., et al.: Attriclip: a non-incremental learner for incremental knowledge learning. In: CVPR, pp. 3654–3663 (2023)
Wang, Z., et al.: Learning to prompt for continual learning. In: CVPR, pp. 139–149 (2022)
Yao, X., et al.: Pcl: proxy-based contrastive learning for domain generalization. In: CVPR, pp. 7097–7107 (2022)
Yoon, J., Madaan, D., Yang, E., Hwang, S.J.: Online coreset selection for rehearsal-based continual learning. arXiv preprint arXiv:2106.01085 (2021)
Yu, L., Hu, T., HONG, L., Liu, Z., Weller, A., Liu, W.: Continual learning by modeling intra-class variation. Trans. Mach. Learn. Res. (2023). https://openreview.net/forum?id=iDxfGaMYVr
Zhang, Y., Pfahringer, B., Frank, E., Bifet, A., Lim, N.J.S., Jia, Y.: A simple but strong baseline for online continual learning: Repeated augmented rehearsal. Adv. Neural. Inf. Process. Syst. 35, 14771–14783 (2022)
Zhao, B., Xiao, X., Gan, G., Zhang, B., Xia, S.T.: Maintaining discrimination and fairness in class incremental learning. In: CVPR, pp. 13208–13217 (2020)
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China (No. 62376218, No. 62101453), Guangdong Basic and Applied Basic Research Foundation (No. 2023A1515011298), Natural Science Basic Research Program of Shaanxi (No. 2022JC-DW-08).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Su, S., Chen, Z., Liang, G., Zhang, S., Zhang, Y. (2025). Dual Supervised Contrastive Learning Based on Perturbation Uncertainty for Online Class Incremental Learning. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds) Pattern Recognition. ICPR 2024. Lecture Notes in Computer Science, vol 15309. Springer, Cham. https://doi.org/10.1007/978-3-031-78189-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-78189-6_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-78188-9
Online ISBN: 978-3-031-78189-6
eBook Packages: Computer ScienceComputer Science (R0)