Memory replay with unlabeled data for semi-supervised class-incremental learning via temporal consistency

Graphical abstract

References

[1] Rebuffi S A, Kolesnikov A, Sperl G, Lampert C H. iCaRL: incremental classifier and representation learning. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017, 5533–5542

[2] Zhao B, Xiao X, Gan G, Zhang B, Xia S T. Maintaining discrimination and fairness in class incremental learning. In: Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020, 13205–13214

[3] Yan S, Xie J, He X. DER: dynamically expandable representation for class incremental learning. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021, 3013–3022

[4] Zhou D W, Ye H J, Zhan D C. Co-transport for class-incremental learning. In: Proceedings of the 29th ACM International Conference on Multimedia. 2021, 1645–1654

[5] Van Engelen J E, Hoos H H . A survey on semi-supervised learning. Machine Learning, 2020, 109( 2): 373–440

[6] Berthelot D, Carlini N, Goodfellow I, Oliver A, Papernot N, Raffel C. MixMatch: a holistic approach to semi-supervised learning. In: Proceedings of the 33rd Conference on Neural Information Processing Systems. 2019, 32

[7] Sohn K, Berthelot D, Li C L, Zhang Z, Carlini N, Cubuk E D, Kurakin A, Zhang H, Raffel C. FixMatch: Simplifying semi-supervised learning with consistency and confidence. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 51

[8] Li Z, Hoiem D . Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40( 12): 2935–2947

[9] Lechat A, Herbin S, Jurie F. Pseudo-labeling for class incremental learning. In: Proceedings of the 32nd British Machine Vision Conference 2021. 2021, 332

[10] Liu W, Zhu F, Liu C L. Towards non-exemplar semi-supervised class-incremental learning. 2024, arXiv preprint arXiv: 2403.18291

RIGHTS & PERMISSIONS

Higher Education Press