Abstract
Lifelong learning, which attempts to alleviate catastrophic forgetting in machine learning models, is gaining increasing attention for deep neural networks. Recent lifelong learning methods which continuously append new classes in the classification layer of deep neural network suffer from the model capacity issue. Representation learning is a feasible solution for this problem. However, representation learning in lifelong learning has not been cautiously evaluated, especially for unseen classes. In this work, we concentrate on evaluating the performance of lifelong representation learning on unseen classes, and propose an effective lifelong representation learning method to match image pairs, without the need of increasing the model capacity. Specifically, we preserve the knowledge of previous tasks in the manifolds learned from multiple network layer outputs. The obtained distributions of these manifolds are further used to generate pseudo feature maps which are replayed in a combination with knowledge distillation strategy to improve the performance. We conduct the experiments on three widely used Person ReID datasets to evaluate the performance of lifelong representation learning on unseen classes. The result shows that our proposed method achieves the state-of-the-art performance compared to other related lifelong learning methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
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., Chakravarty, P., Tuytelaars, T.: Expert gate: Lifelong learning with a network of experts. In: CVPR (2017)
Doersch, C.: Tutorial on variational autoencoders. In: arXiv:1606.05908 (2016)
Grossberg, S.T.: Studies of Mind and Brain: Neural Principles of Learning, Perception. Cognition, and Motor Control. Springer, Development (1982)
Huang, T., Qu, W., Zhang, J.: Continual representation learning via auto-weighted latent embeddings on person reid. In: PRCV (2021)
Jin, X., Lan, C., Zeng, W., Chen, Z., Zhang, L.: Style normalization and restitution for generalizable person re-identification. In: CVPR (2020)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. In: Proceedings of National Academy of Sciences (2017)
Lange, M.D., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., Tuytelaars, T.: Continual learning: A comparative study on how to defy forgetting in classification tasks. arXiv:1909.08383 (2019)
Li, X., Xiong, H., Wang, H., Rao, Y., Liu, L., Chen, Z., Huan, J.: Delta: deep learning transfer using feature map with attention for convolutional networks. In: ICLR (2019)
Li, X., Grandvalet, Y., Davoine, F.: Explicit inductive bias for transfer learning with convolutional networks. In: ICML (2018)
Li, Z., Hoiem, D.: Learning without forgetting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 614–629. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_37
Liu, J., Zha, Z.J., Chen, D., Hong, R., Wang, M.: Adaptive transfer network for cross-domain person re-identificaiton. In: CVPR (2019)
Liu, X., et al.: Generative feature replay for class-incremental learning. In: CVPR Workshop (2020)
Rannen, A., Aljundi, R., Blaschko, M.B., Tuytelaars, T.: Encoder based lifelong learning. In: ICCV (2017)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: icarl: Incremental classifier and representation learning. In: CVPR (2017)
Shin, H., Lee, J.K., Kim, J., Kim, J.: Continual learning with deep generative replay. In: NIPS (2017)
Sugianto, N., Tjondronegoro, D., Sorwar, G., Chakraborty, P., Yuwono, E.I.: Continuous learning without forgetting for person re-identification. In: International Conference on Advanced Video and Signal Based Surveillance (AVSS) (2019)
Yu, L., Twardowski, B., Liu, X., Herranz, L., Wang, K., Cheng, Y., Jui, S., van de Weijer, J.: Semantic drift compensation for class-incremental learning. In: CVPR (2020)
Zhao, B., Tang, S., Chen, D., Bilen, H., Zhao, R.: Continual representation learning for biometric identification. In: WACV (2021)
Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: CVPR (2017)
Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camera style adaptation for person re-identification. In: CVPR (2018)
Acknowledgement
This work is supported by National Key Research and Development Program of China (2021YFF1200804), and National Key Research and Development Program of China (2021YFF1200800).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, T., Zhang, J. (2022). Manifold-Driven and Feature Replay Lifelong Representation Learning on Person ReID. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13535. Springer, Cham. https://doi.org/10.1007/978-3-031-18910-4_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-18910-4_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18909-8
Online ISBN: 978-3-031-18910-4
eBook Packages: Computer ScienceComputer Science (R0)