WePerson: Generalizable Re-Identification From Synthetic Data With Single Query Adaptation

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.