Person Re-ID in 2025: Supervised, Self-Supervised, and Language-Aligned. What Works?

2026-01-28

AI Summary

This study addresses the limited cross-domain generalization of person re-identification (ReID) models by systematically evaluating three training paradigms—supervised learning, self-supervised learning, and language-aligned representation learning—on cross-domain ReID tasks. Through extensive experiments involving 11 representative models and 9 datasets, the authors demonstrate that while conventional supervised models achieve strong performance on source domains, they suffer significant degradation when deployed across domains. In contrast, language-aligned models not explicitly trained for ReID—such as those based on SigLIP—exhibit markedly superior cross-domain robustness. This work is the first to reveal that language alignment can effectively enhance the cross-domain generalization capability of ReID models, offering a novel perspective for unsupervised domain adaptation in person re-identification.

Technology Category

• Computer Vision: Language and Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Person Re-Identification (ReID) remains a challenging problem in computer vision. This work reviews various training paradigm and evaluates the robustness of state-of-the-art ReID models in cross-domain applications and examines the role of foundation models in improving generalization through richer, more transferable visual representations. We compare three training paradigms, supervised, self-supervised, and language-aligned models. Through the study the aim is to answer the following questions: Can supervised models generalize in cross-domain scenarios? How does foundation models like SigLIP2 perform for the ReID tasks? What are the weaknesses of current supervised and foundational models for ReID? We have conducted the analysis across 11 models and 9 datasets. Our results show a clear split: supervised models dominate their training domain but crumble on cross-domain data. Language-aligned models, however, show surprising robustness cross-domain for ReID tasks, even though they are not explicitly trained to do so. Code and data available at: https://github.com/moiiai-tech/object-reid-benchmark.

Problem

• Person Re-Identification
• cross-domain generalization
• foundation models
• robustness
• training paradigms

Innovation

• Person Re-Identification
• Cross-domain Generalization
• Language-aligned Models
• Foundation Models
• Supervised vs Self-supervised Learning