Homocentric Hypersphere Feature Embedding for Person Re-identification
This addresses incremental improvements in feature representation for person re-identification, a domain-specific task in computer vision.
The paper tackled the problem of measure inconsistency and coupled magnitude-orientation information in person re-identification by proposing a homocentric hypersphere embedding scheme, achieving leading performance on benchmarks like Market1501, CUHK03, and DukeMTMC-ReID.
Person re-identification (Person ReID) is a challenging task due to the large variations in camera viewpoint, lighting, resolution, and human pose. Recently, with the advancement of deep learning technologies, the performance of Person ReID has been improved swiftly. Feature extraction and feature matching are two crucial components in the training and deployment stages of Person ReID. However, many existing Person ReID methods have measure inconsistency between the training stage and the deployment stage, and they couple magnitude and orientation information of feature vectors in feature representation. Meanwhile, traditional triplet loss methods focus on samples within a mini-batch and lack knowledge of global feature distribution. To address these issues, we propose a novel homocentric hypersphere embedding scheme to decouple magnitude and orientation information for both feature and weight vectors, and reformulate classification loss and triplet loss to their angular versions and combine them into an angular discriminative loss. We evaluate our proposed method extensively on the widely used Person ReID benchmarks, including Market1501, CUHK03 and DukeMTMC-ReID. Our method demonstrates leading performance on all datasets.