HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification [article]

Jiawei Ren, Xiao Ma, Chen Xu, Haiyu Zhao, Shuai Yi
2021 arXiv   pre-print
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
more » ... 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.
arXiv:2101.02568v2 fatcat:ku3nlq3gozgc3izoea6rb2efxa