Abstract
In order to address real-world problems, deep learning models are jointly trained on many classes. However, in the future, some classes may become restricted due to privacy/ethical concerns, and the restricted class knowledge has to be removed from the models that have been trained on them. The available data may also be limited due to privacy/ethical concerns, and re-training the model will not be possible. We propose a novel approach to address this problem without affecting the model’s prediction power for the remaining classes. Our approach identifies the model parameters that are highly relevant to the restricted classes and removes the knowledge regarding the restricted classes from them using the limited available training data. Our approach is significantly faster and performs similar to the model re-trained on the complete data of the remaining classes.
All the authors have 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
Carreira-Perpinán, M.A., Idelbayev, Y.: “learning-compression” algorithms for neural net pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8532–8541 (2018)
Dong, X., Chen, S., Pan, S.J.: Learning to prune deep neural networks via layer-wise optimal brain surgeon. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS 2017, pp. 4860–4874. Curran Associates Inc., Red Hook (2017)
Douillard, A., Cord, M., Ollion, C., Robert, T., Valle, E.: PODNet: pooled outputs distillation for small-tasks incremental learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 86–102. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_6
Edwards, H., Storkey, A.: Censoring representations with an adversary. arXiv preprint arXiv:1511.05897 (2015)
Ginart, A., Guan, M.Y., Valiant, G., Zou, J.: Making AI forget you: data deletion in machine learning. arXiv preprint arXiv:1907.05012 (2019)
Golatkar, A., Achille, A., Ravichandran, A., Polito, M., Soatto, S.: Mixed-privacy forgetting in deep networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 792–801 (2021)
Guo, Y., Yao, A., Chen, Y.: Dynamic network surgery for efficient DNNs. Adv. Neural. Inf. Process. Syst. 29, 1379–1387 (2016)
Hamm, J.: Minimax filter: learning to preserve privacy from inference attacks. J. Mach. Learn. Res. 18(1), 4704–4734 (2017)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015)
He, Y., Kang, G., Dong, X., Fu, Y., Yang, Y.: Soft filter pruning for accelerating deep convolutional neural networks. In: IJCAI International Joint Conference on Artificial Intelligence (2018)
He, Y., Dong, X., Kang, G., Fu, Y., Yan, C., Yang, Y.: Asymptotic soft filter pruning for deep convolutional neural networks. IEEE Trans. Cybern. 50(8), 3594–3604 (2019)
He, Y., Liu, P., Wang, Z., Hu, Z., Yang, Y.: Filter pruning via geometric median for deep convolutional neural networks acceleration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4340–4349 (2019)
He, Y., Liu, P., Zhu, L., Yang, Y.: Meta filter pruning to accelerate deep convolutional neural networks. arXiv preprint arXiv:1904.03961 (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2014). https://fb56552f-a-62cb3a1a-s-sites.googlegroups.com/site/deeplearningworkshopnips2014/65.pdf
Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Learning a unified classifier incrementally via rebalancing. In: CVPR, pp. 831–839 (2019)
Kemker, R., Kanan, C.: FearNet: brain-inspired model for incremental learning. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=SJ1Xmf-Rb
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)
Liu, Y., Schiele, B., Sun, Q.: Adaptive aggregation networks for class-incremental learning. In: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
Louizos, C., Swersky, K., Li, Y., Welling, M., Zemel, R.: The variational fair autoencoder. arXiv preprint arXiv:1511.00830 (2015)
Nan, L., Tao, D.: Variational approach for privacy funnel optimization on continuous data. J. Parallel Distrib. Comput. 137, 17–25 (2020)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: ICARL: incremental classifier and representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2001–2010 (2017)
Tao, X., Chang, X., Hong, X., Wei, X., Gong, Y.: Topology-preserving class-incremental learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 254–270. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58529-7_16
Wu, Y., et al.: Large scale incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 374–382 (2019)
Yu, L., et al.: Semantic drift compensation for class-incremental learning. In: CVPR, pp. 6982–6991 (2020)
Zhang, T., et al.: A systematic DNN weight pruning framework using alternating direction method of multipliers. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 191–207. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_12
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
Singh, P., Mazumder, P., Karim, M.A. (2022). Attaining Class-Level Forgetting in Pretrained Model Using Few Samples. 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 13673. Springer, Cham. https://doi.org/10.1007/978-3-031-19778-9_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-19778-9_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19777-2
Online ISBN: 978-3-031-19778-9
eBook Packages: Computer ScienceComputer Science (R0)