A Discriminatively Learned CNN Embedding for Person Reidentification
A Discriminatively Learned CNN Embedding for Person Reidentification
We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e, verification and classification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. …