# Lifelong Person Re-Identification via Adaptive Knowledge Accumulation

arXiv: https://arxiv.org/abs/2103.12462 · HTML: https://mlsanity.com/paper/2103.12462/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 55 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 30 of 31)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [Graph Matching Networks for Learning the Similarity of Graph Structured Objects](https://mlsanity.com/paper/1904.12787/) (2019)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Relation-Aware Global Attention for Person Re-identification](https://mlsanity.com/paper/1904.02998/) (2019)
- [Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective](https://mlsanity.com/paper/2002.10826/) (2020)
- [Unsupervised Person Re-identification via Multi-label Classification](https://mlsanity.com/paper/2004.09228/) (2020)
- [Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification](https://mlsanity.com/paper/2007.10315/) (2020)
- [Memory Replay GANs: learning to generate images from new categories without forgetting](https://mlsanity.com/paper/1809.02058/) (2018)
- [A PAC-Bayesian bound for Lifelong Learning](https://mlsanity.com/paper/1311.2838/) (2013)
- [Spectral Feature Transformation for Person Re-identification](https://mlsanity.com/paper/1811.11405/) (2018)
- [Robust Re-Identification by Multiple Views Knowledge Distillation](https://mlsanity.com/paper/2007.04174/) (2020)
- [Continual Representation Learning for Biometric Identification](https://mlsanity.com/paper/2006.04455/) (2020)
- [Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2008.02520/) (2020)
- [On the Exploration of Incremental Learning for Fine-grained Image Retrieval](https://mlsanity.com/paper/2010.08020/) (2020)

## Built on by (most cited first, 30 of 57)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation](https://mlsanity.com/paper/2211.16201/) (2022)
- [Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation](https://mlsanity.com/paper/2112.06632/) (2021)
- [MixDehazeNet : Mix Structure Block For Image Dehazing Network](https://mlsanity.com/paper/2305.17654/) (2023)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges](https://mlsanity.com/paper/2207.11759/) (2022)
- [DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification](https://mlsanity.com/paper/2412.09224/) (2024)
- [Rotation Invariant Transformer for Recognizing Object in UAVs](https://mlsanity.com/paper/2311.02559/) (2023)
- [Continual Learning for Smart City: A Survey](https://mlsanity.com/paper/2404.00983/) (2024)
- [FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning](https://mlsanity.com/paper/2403.16561/) (2024)
- [Online Unsupervised Domain Adaptation for Person Re-identification](https://mlsanity.com/paper/2205.04383/) (2022)
- [Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States](https://mlsanity.com/paper/2405.16600/) (2024)
- [Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification](https://mlsanity.com/paper/2507.01884/) (2025)
- [CL2R: Compatible Lifelong Learning Representations](https://mlsanity.com/paper/2211.09032/) (2022)
- [Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2308.10716/) (2023)
- [Unsupervised Lifelong Person Re-identification via Contrastive Rehearsal](https://mlsanity.com/paper/2203.06468/) (2022)
- [Domain Incremental Lifelong Learning in an Open World](https://mlsanity.com/paper/2305.06555/) (2023)
- [Diverse Representation Embedding for Lifelong Person Re-Identification](https://mlsanity.com/paper/2403.16003/) (2024)
- [Anti-Forgetting Adaptation for Unsupervised Person Re-identification](https://mlsanity.com/paper/2411.14695/) (2024)
- [Fine-Grained Adversarial Semi-supervised Learning](https://mlsanity.com/paper/2110.05848/) (2021)
- [Domain Consistency Representation Learning for Lifelong Person Re-Identification](https://mlsanity.com/paper/2409.19954/) (2024)
- [Real-time Video Target Tracking Algorithm Utilizing Convolutional Neural Networks (CNN)](https://mlsanity.com/paper/2411.18314/) (2024)
- [Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition](https://mlsanity.com/paper/2111.04993/) (2021)
- [Contrastive Supervised Distillation for Continual Representation Learning](https://mlsanity.com/paper/2205.05476/) (2022)
- [Source-Guided Similarity Preservation for Online Person Re-Identification](https://mlsanity.com/paper/2402.15206/) (2024)
- [Auto-selected Knowledge Adapters for Lifelong Person Re-identification](https://mlsanity.com/paper/2405.19005/) (2024)
- [TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2111.14290/) (2021)
- [Style Variable and Irrelevant Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2209.05235/) (2022)

## Abstract (arXiv)

Person 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.