\begin{thebibliography}{10}

\bibitem{Aljundi2019OnlineCL}
R.~Aljundi, L.~Caccia, E.~Belilovsky, M.~Caccia, M.~Lin, L.~Charlin, and
  T.~Tuytelaars.
\newblock Online continual learning with maximally interfered retrieval.
\newblock {\em ArXiv}, abs/1908.04742, 2019.

\bibitem{Aljundi2019GradientBS}
R.~Aljundi, M.~Lin, B.~Goujaud, and Y.~Bengio.
\newblock Gradient based sample selection for online continual learning.
\newblock In {\em NeurIPS}, 2019.

\bibitem{chaudhry2018riemannian}
A.~Chaudhry, P.~K. Dokania, T.~Ajanthan, and P.~H. Torr.
\newblock Riemannian walk for incremental learning: Understanding forgetting
  and intransigence.
\newblock In {\em Proceedings of the European Conference on Computer Vision
  (ECCV)}, pages 532--547, 2018.

\bibitem{kirkpatrick2017overcoming}
J.~Kirkpatrick, R.~Pascanu, N.~Rabinowitz, J.~Veness, G.~Desjardins, A.~A.
  Rusu, K.~Milan, J.~Quan, T.~Ramalho, A.~Grabska-Barwinska, et~al.
\newblock Overcoming catastrophic forgetting in neural networks.
\newblock {\em Proceedings of the national academy of sciences},
  114(13):3521--3526, 2017.

\bibitem{Knoblauch2020OptimalCL}
J.~Knoblauch, H.~Husain, and T.~Diethe.
\newblock Optimal continual learning has perfect memory and is np-hard.
\newblock In {\em ICML}, 2020.

\bibitem{li2017learning}
Z.~Li and D.~Hoiem.
\newblock Learning without forgetting.
\newblock {\em IEEE transactions on pattern analysis and machine intelligence},
  40(12):2935--2947, 2017.

\bibitem{Lomonaco2020RehearsalFreeCL}
V.~Lomonaco, D.~Maltoni, and L.~Pellegrini.
\newblock Rehearsal-free continual learning over small non-i.i.d. batches.
\newblock {\em 2020 IEEE/CVF Conference on Computer Vision and Pattern
  Recognition Workshops (CVPRW)}, pages 989--998, 2020.

\bibitem{Lomonaco2020CVPR2C}
V.~Lomonaco, L.~Pellegrini, P.~Rodr{\'i}guez, M.~Caccia, Q.~She, Y.~Chen,
  Q.~Jodelet, R.~Wang, Z.~Mai, D.~V{\'a}zquez, G.~I. Parisi, N.~Churamani,
  M.~Pickett, I.~H. Laradji, and D.~Maltoni.
\newblock Cvpr 2020 continual learning in computer vision competition:
  Approaches, results, current challenges and future directions.
\newblock {\em ArXiv}, abs/2009.09929, 2020.

\bibitem{lopez2017gradient}
D.~Lopez-Paz and M.~Ranzato.
\newblock Gradient episodic memory for continual learning.
\newblock volume~30, pages 6467--6476, 2017.

\bibitem{Maltoni2019ContinuousLI}
D.~Maltoni and V.~Lomonaco.
\newblock Continuous learning in single-incremental-task scenarios.
\newblock {\em Neural networks : the official journal of the International
  Neural Network Society}, 116:56--73, 2019.

\bibitem{Pellegrini2020LatentRF}
L.~Pellegrini, G.~Graffieti, V.~Lomonaco, and D.~Maltoni.
\newblock Latent replay for real-time continual learning.
\newblock {\em 2020 IEEE/RSJ International Conference on Intelligent Robots and
  Systems (IROS)}, pages 10203--10209, 2020.

\bibitem{Pelosin2021MoreIB}
F.~Pelosin and A.~Torsello.
\newblock More is better: An analysis of instance quantity/quality trade-off in
  rehearsal-based continual learning.
\newblock {\em ArXiv}, abs/2105.14106, 2021.

\bibitem{Prabhu2020GDumbAS}
A.~Prabhu, P.~H.~S. Torr, and P.~Dokania.
\newblock Gdumb: A simple approach that questions our progress in continual
  learning.
\newblock In {\em ECCV}, 2020.

\bibitem{rebuffi2017icarl}
S.-A. Rebuffi, A.~Kolesnikov, G.~Sperl, and C.~H. Lampert.
\newblock icarl: Incremental classifier and representation learning.
\newblock In {\em Proceedings of the IEEE conference on Computer Vision and
  Pattern Recognition}, pages 2001--2010, 2017.

\bibitem{shin2017continual}
H.~Shin, J.~K. Lee, J.~Kim, and J.~Kim.
\newblock Continual learning with deep generative replay.
\newblock {\em arXiv preprint arXiv:1705.08690}, 2017.

\bibitem{zenke2017continual}
F.~Zenke, B.~Poole, and S.~Ganguli.
\newblock Continual learning through synaptic intelligence.
\newblock In {\em International Conference on Machine Learning}, pages
  3987--3995. PMLR, 2017.

\end{thebibliography}