Lifelong Person Re-Identification via Adaptive Knowledge Accumulation

By Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew. 2021

121 citations recorded by the source corpus.

Person re-identification (ReID) methods always learn through a stationary domain that is fixed by the choice of a given dataset. In many contexts (e.g., lifelong learning), those methods are ineffective because the domain is continually changing in which case incremental learning over multiple domains is required potentially. In this work we explore a new and challenging ReID task, namely lifelong person re-identification (LReID), which enables to learn continuously across multiple domains and even generalise on new and unseen domains. Following the cognitive processes in the human brain, we design an Adaptive Knowledge Accumulation (AKA) framework that is endowed with two crucial abilities: knowledge representation and knowledge operation. Our method alleviates catastrophic forgetting on seen domains and demonstrates the ability to generalize to unseen domains. Correspondingly, we also provide a new and large-scale benchmark for LReID. Extensive experiments demonstrate our method outperforms other competitors by a margin of 5.8% mAP in generalising evaluation. The codes will be available at https://github.com/TPCD/LifelongReID.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Qiwen Wang
5. Ziwei Liu
6. Zhiyuan Qi
7. Zhi-Hong Qi
8. Yadong Mu

In Computer Vision and Pattern Recognition

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Qiwen Wang
5. Ziwei Liu
6. Zhiyuan Qi
7. Zhi-Hong Qi
8. Yadong Mu

Citations in the corpus

• Recent Advances of Continual Learning in Computer Vision: An Overview (2021, neutral): “[70] proposed to apply knowledge distillation on person re-identification.”
• Class-Incremental Learning: A Survey (2023, methodology): “Due to their flexibility, knowledge distillation-based methods have also been widely applied to various incremental learning tasks, e.g. , semantic segmentation [193], person re-identification [194], human action recognition [91], and federated learning [149].”
• Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification (2024, methodology): “In this section, we compared our C 2 R with several state-of-the-art methods on both RFL-ReID and traditional L-ReID tasks, including SPD [28], LwF [11], CRL [40], AKA [18], MEGE [20], PatchKD [27], and CVS [30], where CSV is a continual compatible training method and the others are L-ReID methods.”
• Deep Class-Incremental Learning: A Survey (2023, background): “, semantic segmentation [164], [165], [166], [167], person re-identification [168], [169], human action recognition [95], and federated learning [137].”
• Patch-based Knowledge Distillation for Lifelong Person Re-Identification (2022, methodology): “[46] maintain a learnable knowledge graph to accumulate previous knowledge and generalize to unseen domains.”