Domain Adaptation through Synthesis for Unsupervised Person Re-identification
This addresses the challenge of illumination variability in surveillance camera systems for person re-identification, offering an incremental improvement through synthetic data and unsupervised adaptation.
The paper tackles the problem of person re-identification under varying illumination conditions by introducing a synthetic dataset with hundreds of lighting variations and a novel unsupervised domain adaptation technique, achieving significantly higher accuracy than semi-supervised and unsupervised state-of-the-art methods and being competitive with supervised techniques.
Drastic variations in illumination across surveillance cameras make the person re-identification problem extremely challenging. Current large scale re-identification datasets have a significant number of training subjects, but lack diversity in lighting conditions. As a result, a trained model requires fine-tuning to become effective under an unseen illumination condition. To alleviate this problem, we introduce a new synthetic dataset that contains hundreds of illumination conditions. Specifically, we use 100 virtual humans illuminated with multiple HDR environment maps which accurately model realistic indoor and outdoor lighting. To achieve better accuracy in unseen illumination conditions we propose a novel domain adaptation technique that takes advantage of our synthetic data and performs fine-tuning in a completely unsupervised way. Our approach yields significantly higher accuracy than semi-supervised and unsupervised state-of-the-art methods, and is very competitive with supervised techniques.