Lifelong Person Re-identification via Privacy-Preserving Data Replay

• URL: http://arxiv.org/abs/2508.01587v1
• Date: Sun, 03 Aug 2025 05:00:19 GMT
• Title: Lifelong Person Re-identification via Privacy-Preserving Data Replay
• Authors: Mingyu Wang, Haojie Liu, Zhiyong Li, Wei Jiang,
• Abstract summary: Lifelong person re-identification (LReID) aims to incrementally accumulate knowledge across a sequence of tasks under domain shifts.<n>Recent replay-based methods have demonstrated strong effectiveness in LReID by rehearsing past samples stored in an auxiliary memory.<n>We propose to condense information from sequential data into the pixel space in the replay memory, enabling Privacy-Preserving Replay (Pr2R)
• Score: 14.764580534110666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lifelong person re-identification (LReID) aims to incrementally accumulate knowledge across a sequence of tasks under domain shifts. Recently, replay-based methods have demonstrated strong effectiveness in LReID by rehearsing past samples stored in an auxiliary memory. However, storing historical exemplars raises concerns over data privacy. To avoid this, exemplar-free approaches attempt to match the distribution of past data without storing raw samples. Despite being privacy-friendly, these methods often suffer from performance degradation due to the forgetting of specific past knowledge representations. To this end, we propose to condense information from sequential data into the pixel space in the replay memory, enabling Privacy-Preserving Replay (Pr^2R). More specifically, by distilling the training characteristics of multiple real images into a single image, the condensed samples undergo pixel-level changes. This not only protects the privacy of the original data but also makes the replay samples more representative for sequential tasks. During the style replay phase, we align the current domain to the previous one while simultaneously adapting the replay samples to match the style of the current domain. This dual-alignment strategy effectively mitigates both class-incremental challenges and forgetting caused by domain shifts. Extensive experiments on multiple benchmarks show that the proposed method significantly improves replay effectiveness while preserving data privacy. Specifically, Pr^2R achieves 4% and 6% higher accuracy on sequential tasks compared to the current state-of-the-art and other replay-based methods, respectively.

Related papers

• When Person Re-Identification Meets Event Camera: A Benchmark Dataset and An Attribute-guided Re-Identification Framework [82.9994467829281]
  This paper introduces a large-scale RGB-event based person ReID dataset, called EvReID.<n>The dataset contains 118,988 image pairs and covers 1200 pedestrian identities, with data collected across multiple seasons, scenes, and lighting conditions.<n>We also evaluate 15 state-of-the-art person ReID algorithms, laying a solid foundation for future research in terms of both data and benchmarking.
  arXiv  Detail & Related papers  (2025-07-18T05:04:59Z)
• Continual Learning of Personalized Generative Face Models with Experience Replay [1.024113475677323]
  We introduce a novel continual learning problem: how to sequentially update the weights of a personalized 2D and 3D generative face model.<n>We observe that naive sequential fine-tuning of the model leads to catastrophic forgetting of past representations of the individual's face.<n>We propose a novel experience replay algorithm that combines random sampling with StyleGAN's latent space to represent the buffer as an optimal convex hull.
  arXiv  Detail & Related papers  (2024-12-03T17:56:23Z)
• Prioritized Generative Replay [121.83947140497655]
  We propose a prioritized, parametric version of an agent's memory, using generative models to capture online experience.<n>This paradigm enables densification of past experience, with new generations that benefit from the generative model's generalization capacity.<n>We show this recipe can be instantiated using conditional diffusion models and simple relevance functions.
  arXiv  Detail & Related papers  (2024-10-23T17:59:52Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [93.90047628101155]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks.<n>To address this, some methods propose replaying data from previous tasks during new task learning.<n>However, it is not expected in practice due to memory constraints and data privacy issues.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Summarizing Stream Data for Memory-Constrained Online Continual Learning [17.40956484727636]
  We propose to Summarize the knowledge from the Stream Data (SSD) into more informative samples by distilling the training characteristics of real images. We demonstrate that with limited extra computational overhead, SSD provides more than 3% accuracy boost for sequential CIFAR-100 under extremely restricted memory buffer.
  arXiv  Detail & Related papers  (2023-05-26T05:31:51Z)
• Memory Replay with Data Compression for Continual Learning [80.95444077825852]
  We propose memory replay with data compression to reduce the storage cost of old training samples. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.
  arXiv  Detail & Related papers  (2022-02-14T10:26:23Z)
• Replay For Safety [51.11953997546418]
  In experience replay, past transitions are stored in a memory buffer and re-used during learning. We show that using an appropriate biased sampling scheme can allow us to achieve a emphsafe policy.
  arXiv  Detail & Related papers  (2021-12-08T11:10:57Z)
• Continual Learning for Fake Audio Detection [62.54860236190694]
  This paper proposes detecting fake without forgetting, a continual-learning-based method, to make the model learn new spoofing attacks incrementally. Experiments are conducted on the ASVspoof 2019 dataset.
  arXiv  Detail & Related papers  (2021-04-15T07:57:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.