2021/01/06 by Jiawei Ren, Xiao Ma, Ren, Jiawei +7
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Fire Detection and Safety Systems #Human Pose and Action Recognition #Machine Learning (cs.LG) #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2101.02568
openalex publication_date 2021/01/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Person Re-Identification (Re-ID) is of great importance to the many video surveillance systems. Learning discriminative features for Re-ID remains a challenge due to the large variations in the image space, e.g., continuously changing human poses, illuminations and point of views. In this paper, we propose HAVANA, a novel extensible, light-weight HierArchical and VAriation-Normalized Autoencoder that learns features robust to intra-class variations. In contrast to existing generative approaches that prune the variations with heavy extra supervised signals, HAVANA suppresses the intra-class variations with a Variation-Normalized Autoencoder trained with no additional supervision. We also introduce a novel Jensen-Shannon triplet loss for contrastive distribution learning in Re-ID. In addition, we present Hierarchical Variation Distiller, a hierarchical VAE to factorize the latent representation and explicitly model the variations. To the best of our knowledge, HAVANA is the first VAE-based framework for person ReID.