WePerson: Generalizable Re-Identification From Synthetic Data With Single Query Adaptation
- 11 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 7 (3) , 458-470
Abstract
Person re-identification (ReID) aims to retrieve a target person across non-overlapping cameras. Due to the uncontrollable environment and the privacy concerns, the diversity and scale of real-world training data are usually limited, resulting in poor testing generalizability. To overcome these problems, we introduce a large-scale Weather Person dataset that generates synthetic images with different weather conditions, complex scenes, natural lighting changes, and various pedestrian accessories in a simulated camera network. The environment is fully controllable, supporting factor-by-factor analysis. To narrow the gap between synthetic data and real-world scenarios, this paper introduces a simple yet efficient domain generalization method via Single Query Adaptation (SQA), calibrating the statistics and transformation parameters in BatchNorm layers with only a single query image in the target domain. This significantly improves performance through a single adaptation epoch, greatly boosting the applicability of the ReID technique for intelligent surveillance systems. Abundant experiment results demonstrate that the WePerson dataset achieves superior performance under direct transfer setting without any real-world data training. In addition, the proposed SQA method shows amazing robustness in real-to-real, synthetic-to-real ReID, and various corruption settings. Dataset and code are available at https://github.com/lihe404/WePerson.Keywords
Funding Information
- National Key Research and Development Program of China (2024YFC3308400)
- National Natural Science Foundation of China (62176188, 62225113)
This publication has 48 references indexed in Scilit:
- Interpretable and Generalizable Person Re-identification with Query-Adaptive Convolution and Temporal Lifting2020
- Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-identification2020
- Rethinking the Distribution Gap of Person Re-identification with Camera-Based Batch Normalization2020
- Domain Adaptation Through Synthesis for Unsupervised Person Re-identification2018
- Person Transfer GAN to Bridge Domain Gap for Person Re-identification2018
- Looking beyond appearances: Synthetic training data for deep CNNs in re-identificationComputer Vision and Image Understanding, 2018
- Re-ranking Person Re-identification with k-Reciprocal Encoding2017
- Performance Measures and a Data Set for Multi-target, Multi-camera Tracking2016
- Evaluation Methods in Face Recognition2011
- Innovations in Computing Sciences and Software Engineering2010