# Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification

arXiv: https://arxiv.org/abs/2504.15041 · HTML: https://mlsanity.com/paper/2504.15041/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for continual learning, one of 12 directions in Knowledge distillation.
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Placed in

- Knowledge distillation / [Distillation for continual learning](https://mlsanity.com/distill/distillation-for-continual-learning/)

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [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)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://mlsanity.com/paper/2401.15947/) (2024)
- [S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning](https://mlsanity.com/paper/2207.12819/) (2022)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters](https://mlsanity.com/paper/2403.11549/) (2024)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)
- [LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training](https://mlsanity.com/paper/2406.16554/) (2024)
- [Occluded Person Re-identification](https://mlsanity.com/paper/1804.02792/) (2018)
- [Lifelong Person Re-Identification via Adaptive Knowledge Accumulation](https://mlsanity.com/paper/2103.12462/) (2021)
- [Consistent Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2403.08568/) (2024)
- [Introducing Language Guidance in Prompt-based Continual Learning](https://mlsanity.com/paper/2308.15827/) (2023)
- [Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference](https://mlsanity.com/paper/2211.15969/) (2022)
- [Mixture of Experts Meets Prompt-Based Continual Learning](https://mlsanity.com/paper/2405.14124/) (2024)
- [Convolutional Prompting meets Language Models for Continual Learning](https://mlsanity.com/paper/2403.20317/) (2024)
- [Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation](https://mlsanity.com/paper/2211.16201/) (2022)
- [Continual Representation Learning for Biometric Identification](https://mlsanity.com/paper/2006.04455/) (2020)
- [DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification](https://mlsanity.com/paper/2412.09224/) (2024)
- [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)
- [Domain Consistency Representation Learning for Lifelong Person Re-Identification](https://mlsanity.com/paper/2409.19954/) (2024)
- [Auto-selected Knowledge Adapters for Lifelong Person Re-identification](https://mlsanity.com/paper/2405.19005/) (2024)

## Built on by (most cited first, 2 of 2)

- [Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification](https://mlsanity.com/paper/2605.05027/) (2026)
- [Re:Cognize -- Open-Set Comic Character Re-Identification](https://mlsanity.com/paper/2609.34032/) (2026)

## Abstract (arXiv)

Lifelong Person Re-identification (LReID) suffers from a key challenge in preserving old knowledge while adapting to new information. The existing solutions include rehearsal-based and rehearsal-free methods to address this challenge. Rehearsal-based approaches rely on knowledge distillation, continuously accumulating forgetting during the distillation process. Rehearsal-free methods insufficiently learn the distribution of each domain, leading to forgetfulness over time. To solve these issues, we propose a novel Distribution-aware Forgetting Compensation (DAFC) model that explores cross-domain shared representation learning and domain-specific distribution integration without using old exemplars or knowledge distillation. We propose a Text-driven Prompt Aggregation (TPA) that utilizes text features to enrich prompt elements and guide the prompt model to learn fine-grained representations for each instance. This can enhance the differentiation of identity information and establish the foundation for domain distribution awareness. Then, Distribution-based Awareness and Integration (DAI) is designed to capture each domain-specific distribution by a dedicated expert network and adaptively consolidate them into a shared region in high-dimensional space. In this manner, DAI can consolidate and enhance cross-domain shared representation learning while alleviating catastrophic forgetting. Furthermore, we develop a Knowledge Consolidation Mechanism (KCM) that comprises instance-level discrimination and cross-domain consistency alignment strategies to facilitate model adaptive learning of new knowledge from the current domain and promote knowledge consolidation learning between acquired domain-specific distributions, respectively. Experimental results show that our DAFC outperforms state-of-the-art methods. Our code is available at https://github.com/LiuShiBen/DAFC.