Abstract
In the real world, training data for person re-identification (ReID) comes in streams and the domain distribution may be inconsistent, which requires the model to incrementally learn new knowledge without forgetting the old knowledge. The problem is known as lifelong person re-identification (LReID). Previous work has focused more on the acquisition of task-irrelevant knowledge and neglected the auxiliary role of task-relevant information in alleviating catastrophic forgetting. To alleviating forgetting and improving the generalization ability, we introduced the prompt to learn task-relevant information, which can guide the model to perform task conditionally. We also proposed a special distillation module for the specific vision transformer structure, which further mitigated catastrophic forgetting. Extensive experiments on twelve person re-identification datasets outperforms other state-of-the-art competitors by a margin of 4.7% average mAP in anti-forgetting evaluation and 7.1% average mAP in generalising evaluation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Li, W., Zhu, X., Gong, S.: Harmonious attention network for person re-identification. In: CVPR, pp. 2285–2294 (2018)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2018)
Zhao, B., **ao, X., Gan, G., Zhang, B., **a, S.: Maintaining discrimination and fairness in class incremental learning. In: CVPR, pp. 13208–13217 (2020)
Serrá, J., Surís, D., Miron, M., Karatzoglou, A.: Overcoming catastrophic forgetting with hard attention to the task. In: ICML, pp. 4548–4557 (2018)
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., Lampert, C.H.: Incremental classifier and representation learning. In: CVPR, pp. 5533–5542 (2017)
Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Learning a unified classifier incrementally via rebalancing. In: CVPR, 831–839 (2019)
Wang, Y., Huang, Z., et al. S:-prompts learning with pre-trained transformers: an Occam’s Razor for domain incremental learning. In: NeurIPS, pp. 5682–5695 (2022)
Bahng, H., Jahanian, A., Sankaranarayanan, S.: Visual prompting: modifying pixel space to adapt pre-trained models. ar**v preprint ar**v:2203.17274 (2022)
Huang, T., Chu, J., Wei, F.: Unsupervised prompt learning for vision-language models. ar**v preprint ar**v:2204.03649 (2022)
Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: CVPR, pp. 3967–3976 (2019)
Wang, Z., Zhang, Z., Lee, C.-Y., Zhang, H., et al.: Learning to prompt for continual learning. In: CVPR, pp. 139–149 (2022)
He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: Transreid: transformer-based object re-identification. In: ICCV, pp. 15013–15022 (2021)
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., et al.: Fitnets: hints for thin deep nets. ar**v preprint ar**v:1412.6550 (2014)
Pu, N., Chen, W., Liu, Y., Bakker, E.M., Lew, M.S.: Generalising without forgetting for lifelong person re-identification. In: AAAI, pp. 2889–2897 (2021)
Pu, N., Chen, W., Liu, Y., Bakker, E.M., Lew, M.S.: Lifelong person re-identification via adaptive knowledge accumulation. In: CVPR, pp. 7901–7910 (2021)
Song, J., Yang, Y., Song, Y.-Z., ** network. In: CVPR, pp. 719–728 (2019)
Castro, F.M., Marín-Jiménez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: ECCV, pp. 233–248 (2018)
Lopez-Paz, D., Ranzato, M.A.: Gradient episodic memory for continual learning. In: NeurIPS, pp. 6470–6479 (2017)
Liu, Y., Cao, J., Li, B., Yuan, C., et al.: Knowledge distillation via instance relationship graph. In: CVPR, pp. 7096–7104 (2019)
Kim, Y., Park, J., Jang, Y., Ali, M., et al.: Distilling global and local logits with densely connected relations. In: ICCV, pp. 6290–6300 (2021)
Hinton, G., Vinyals, O., Dean, J., et al.: Distilling the knowledge in a neural network. ar**v preprint ar**v:1503.02531 (2015)
Ba, J., Caruana, R.: Do deep nets really need to be deep? In: NeurIPS, pp. 2654–2662 (2014)
Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 262–275. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88682-2_21
Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Heyden, A., Kahl, F. (eds.) Image Analysis, pp. 91–102. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21227-7_9
Loy, C.C., **ang, T., Gong, S.: Time-delayed correlation analysis for multi-camera activity understanding. In: IJCV, pp. 106–129 (2010)
Zheng, W.-S., et al.: Associating groups of people. In: BMVC, pp. 1–11 (2009)
Li, W., Zhao, R., Wang, X.: Human re-identification with transferred metric learning. In: ACCV, pp. 31–44 (2012)
Li, W., Wang, X.: Locally aligned feature transforms across views. In: CVPR, pp. 3594–3601 (2013)
Zhao, H., Tian, M., et al.: Spindle net: person re-identification with human body region guided feature decomposition and fusion. In: CVPR, pp. 1077–1085 (2017)
Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: ICCV, pp. 1365–1374 (2019)
Li, Z., et al.: Learning without forgetting. In: TPAMI, pp. 2935–2947 (2017)
Zhao, B., Tang, S., Chen, D., Bilen, H., Zhao, R.: Continual representation learning for biometric identification. In: WACV, pp. 1198–1208 (2021)
Sun, Z., Mu, Y.: Patch-based Knowledge distillation for lifelong person re-identification. In: ACM MM, pp. 696–707 (2022)
Russakovsky, O., Deng, J., Su, H., Krause, J., et al.: Imagenet large scale visual recognition challenge. In: IJCV, pp. 211–252 (2015)
Dai, Y., Liu, J., Sun, Y., Tong, Z., et al.: IDM: an intermediate domain module for domain adaptive person re-id. In: ICCV, pp. 11864–11874 (2021)
Ge, Y., et al.: Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. ar**v preprint ar**v:2001.01526 (2020)
Li, W., Zhao, R., **ao, T., Wang, X.: Deepreid: deep filter pairing neural network for person re-identification. In: CVPR, pp. 152–159 (2014)
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV, pp. 1116–1124 (2015)
**ao, T., Li, S., Wang, B., Lin, L., Wang, X.: End-to-end deep learning for person search. ar**v preprint ar**v:1604.01850 (2016)
Ristani, E., Solera, F., Zou, R., Cucchiara, R.: Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV, pp. 17–35 (2016)
Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer gan to bridge domain gap for person re-identification. In: CVPR, pp. 79–88 (2018)
Acknowledgements
This work was supported by National Key R &D Program of China (No. 2022ZD0118202), the National Science Fund for Distinguished Young Scholars (No. 62025603), the National Natural Science Foundation of China (No. U21B2037, No. U22B2051, No. 62176222, No. 62176223, No. 62176226, No. 62072386, No. 62072387, No. 62072389, No. 62002305 and No. 62272401), and the Natural Science Foundation of Fujian Province of China (No. 2021J01002, No. 2022J06001).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, C., Zhang, Y., Dai, P. (2024). Prompt Based Lifelong Person Re-identification. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14436. Springer, Singapore. https://doi.org/10.1007/978-981-99-8555-5_33
Download citation
DOI: https://doi.org/10.1007/978-981-99-8555-5_33
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8554-8
Online ISBN: 978-981-99-8555-5
eBook Packages: Computer ScienceComputer Science (R0)