Learning a Semantically Discriminative Joint Space for Attribute Based Person Re-identification
share
Attribute based person re-identification (Re-ID) aims to search persons in large-scale image databases using attribute queries. Despite the great practical significance,the huge gap between semantic attributes and visual images makes it a very challenging task. Existing researches usually focus on the match between query attributes and attributes scores predicted from human images, which suffers from imperfect attribute prediction and low discriminability. In this work, we propose to formulate the attribute based person Re-ID as a joint space learning problem. To alleviate the negative impact resulted by the huge heterogeneous gap between different modalities, we apply a novel adversary training strategy to generate homogeneous features for both modalities, providing distribution alignment between different modalities in the feature level and keeping semantic consistency across modalities. Our experiments validate the effectiveness of our model, and show great improvement on the performance over the state of the art models.
READ FULL TEXT