Margin CosReid Network for Pedestrian Re-Identification

Margin CosReid Network for Pedestrian Re-Identification

This paper proposes a margin CosReid network for effective pedestrian re-identification. Aiming to overcome the overfitting, gradient explosion, and loss function non-convergence problems caused by traditional CNNs, the proposed GBNeck model can realize a faster, stronger generalization, and more di...

Full description

Bibliographic Details
Main Authors: Xiao Yun, Min Ge, Yanjing Sun, Kaiwen Dong, Xiaofeng Hou
Format: Article
Language:English
Published: MDPI AG 2021-02-01
Series:Applied Sciences
Subjects:
pedestrian re-identification
CNN
softmax loss
Online Access:https://www.mdpi.com/2076-3417/11/4/1775

Internet

https://www.mdpi.com/2076-3417/11/4/1775

Similar Items