Homocentric Hypersphere Feature Embedding for Person Re-identification

04/24/2018
by   Wangmeng Xiang, et al.
0

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.

READ FULL TEXT

page 4

page 6

page 7

page 8

page 9

page 10

research
06/01/2020

Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification

RGB-Infrared person re-identification (RGB-IR ReID) is a cross-modality ...
research
03/08/2021

Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification

Visible-Infrared cross-modality person re-identification (VI-ReID), whos...
research
11/17/2019

Distribution Context Aware Loss for Person Re-identification

To learn the optimal similarity function between probe and gallery image...
research
08/15/2020

Cluster-level Feature Alignment for Person Re-identification

Instance-level alignment is widely exploited for person re-identificatio...
research
03/26/2021

Leaning Compact and Representative Features for Cross-Modality Person Re-Identification

This paper pays close attention to the cross-modality visible-infrared p...
research
05/12/2020

ReadNet:Towards Accurate ReID with Limited and Noisy Samples

Person re-identification (ReID) is an essential cross-camera retrieval t...
research
06/24/2019

Resolution-invariant Person Re-Identification

Exploiting resolution invariant representation is critical for person Re...

Please sign up or login with your details

Forgot password? Click here to reset