Abstract
Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In this paper, we introduce the novel problem of Memory-Constrained Online Continual Learning (MC-OCL) which imposes strict constraints on the memory overhead that a possible algorithm can use to avoid catastrophic forgetting. As most, if not all, previous CL methods violate these constraints, we propose an algorithmic solution to MC-OCL: Batch-level Distillation (BLD), a regularization-based CL approach, which effectively balances stability and plasticity in order to learn from data streams, while preserving the ability to solve old tasks through distillation. Our extensive experimental evaluation, conducted on three publicly available benchmarks, empirically demonstrates that our approach successfully addresses the MC-OCL problem and achieves comparable accuracy to prior distillation methods requiring higher memory overhead (Code available at https://github.com/DonkeyShot21/batch-level-distillation).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 144–161. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_9
Aljundi, R., et al.: Online continual learning with maximal interfered retrieval. In: NeurIPS, pp. 11849–11860 (2019)
Aljundi, R., Kelchtermans, K., Tuytelaars, T.: Task-free continual learning. In: CVPR (2019)
Aljundi, R., Lin, M., Goujaud, B., Bengio, Y.: Gradient based sample selection for online continual learning. In: NeurIPS (2019)
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
Cermelli, F., Mancini, M., Bulo, S.R., Ricci, E., Caputo, B.: Modeling the background for incremental learning in semantic segmentation. In: CVPR, pp. 9233–9242 (2020)
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
Dhar, P., Singh, R.V., Peng, K.C., Wu, Z., Chellappa, R.: Learning without memorizing. In: CVPR (2019)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2000)
Farquhar, S., Gal, Y.: Towards robust evaluations of continual learning. arXiv preprint arXiv:1805.09733 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. stat (2015)
Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Learning a unified classifier incrementally via rebalancing. In: CVPR (2019)
Javed, K., White, M.: Meta-learning representations for continual learning. In: NeurIPS, pp. 1820–1830 (2019)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. In: PNAS (2017)
Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report (2009)
Lange, M.D., et al.: Continual learning: a comparative study on how to defy forgetting in classification tasks. arXiv:1909.08383 (2019)
LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http://yann.lecun.com/exdb/mnist/
Lee, S., Ha, J., Zhang, D., Kim, G.: A neural dirichlet process mixture model for task-free continual learning. In: ICLR (2020)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE T-PAMI 40(12), 2935–2947 (2017)
Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: NIPS (2017)
Mallya, A., Lazebnik, S.: PackNet: adding multiple tasks to a single network by iterative pruning. In: CVPR (2018)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS (2011)
Ostapenko, O., Puscas, M., Klein, T., Jahnichen, P., Nabi, M.: Learning to remember: a synaptic plasticity driven framework for continual learning. In: CVPR (2019)
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: CVPR (2017)
Riemer, M., et al.: Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910 (2018)
Rusu, A.A., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)
Shin, H., Lee, J.K., Kim, J., Kim, J.: Continual learning with deep generative replay. In: NeurIPS (2017)
Wu, C., Herranz, L., Liu, X., van de Weijer, J., Raducanu, B., et al.: Memory replay GANs: learning to generate new categories without forgetting. In: NeurIPS (2018)
Wu, Y., et al.: Large scale incremental learning. In: CVPR (2019)
Acknowledgements
We acknowledge financial support from the European Institute of Innovation & Technology (EIT) and the H2020 EU project SPRING - Socially Pertinent Robots in Gerontological Healthcare. This work was carried out under the “Vision and Learning joint Laboratory” between FBK and UNITN.
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
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Fini, E., Lathuilière, S., Sangineto, E., Nabi, M., Ricci, E. (2020). Online Continual Learning Under Extreme Memory Constraints. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12373. Springer, Cham. https://doi.org/10.1007/978-3-030-58604-1_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-58604-1_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58603-4
Online ISBN: 978-3-030-58604-1
eBook Packages: Computer ScienceComputer Science (R0)