mlsanityData to 14 Oct 2026

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

arXiv 2604.26363 ↗First posted 29 Apr 2026cs.CV cs.LGcited by 0

Not on the map. Why?

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.

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

20 of 32 references.

References · 20

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2021Model-Contrastive Federated Learningcited by 766
  5. 2021Domain Generalization with MixStylecited by 566
  6. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  7. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  8. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 430
  9. 2022CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labelscited by 181
  10. 2020Style Normalization and Restitution for Generalizable Person Re-identificationcited by 136
  11. 2020Meta Batch-Instance Normalization for Generalizable Person Re-Identificationcited by 77
  12. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
8 more
  1. 2020Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classificationcited by 63
  2. 2022NFormer: Robust Person Re-identification with Neighbor Transformercited by 57
  3. 2020Performance Optimization for Federated Person Re-identification via Benchmark Analysiscited by 50
  4. 2023Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learningcited by 40
  5. 2021CrossNorm and SelfNorm for Generalization under Distribution Shiftscited by 33
  6. 2024DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learningcited by 32
  7. 2020Deep Multi-View Enhancement Hashing for Image Retrievalcited by 27
  8. 2020Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identificationcited by 16

Built on by

Not cited yet.