# CO-EVO: Co-evolving Semantic Anchoring and Style Diversification for Federated DG-ReID

arXiv: https://arxiv.org/abs/2604.26363 · HTML: https://mlsanity.com/paper/2604.26363/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Meta Batch-Instance Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2011.14670/) (2020)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification](https://mlsanity.com/paper/2010.05785/) (2020)
- [NFormer: Robust Person Re-identification with Neighbor Transformer](https://mlsanity.com/paper/2204.09331/) (2022)
- [Performance Optimization for Federated Person Re-identification via Benchmark Analysis](https://mlsanity.com/paper/2008.11560/) (2020)
- [Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning](https://mlsanity.com/paper/2309.16286/) (2023)
- [CrossNorm and SelfNorm for Generalization under Distribution Shifts](https://mlsanity.com/paper/2102.02811/) (2021)
- [DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning](https://mlsanity.com/paper/2403.08506/) (2024)
- [Deep Multi-View Enhancement Hashing for Image Retrieval](https://mlsanity.com/paper/2002.00169/) (2020)
- [Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification](https://mlsanity.com/paper/2006.04150/) (2020)

## Abstract (arXiv)

Federated domain generalization for person re-identification (FedDG-ReID) aims to collaboratively train a pedestrian retrieval model across multiple decentralized source domains such that it can generalize to unseen target environments without compromising raw data privacy. However, this task is significantly challenged by the inherent stylistic gaps across decentralized clients. Without global supervision, models easily succumb to shortcut learning where representations overfit to domain specific camera biases rather than universal identity features. We propose CO-EVO, a novel federated framework that resolves this semantic-style conflict through a co-evolutionary mechanism. On the semantic side, Camera-Invariant Semantic Anchoring (CSA) learns identity prompts with cross-camera consistency to establish purified and domain-agnostic anchors that filter out local imaging noise. On the visual side, Global Style Diversification (GSD), powered by a Global Camera-Style Bank (GCSB), synthesizes realistic perturbations to expand the visual boundaries of training data. The core of CO-EVO is its co-evolutionary loop where purified anchors act as gravitational centers to guide the image encoder toward robust anatomical attributes amidst diverse style variations. Extensive experiments demonstrate that CO-EVO achieves state-of-the-art (SOTA) performance, proving that the synergy between semantic purification and style expansion is essential for robust cross-domain generalization. Our code is available at: https://github.com/NanYiyuzurn/ACL-LGPS-2026.