KDAS-ReID: Architecture Search for Person Re-Identification via Distilled Knowledge with Dynamic Temperature

KDAS-ReID: Architecture Search for Person Re-Identification via Distilled Knowledge with Dynamic Temperature

Person re-Identification(Re-ID) based on deep convolutional neural networks (CNNs) achieves remarkable success with its fast speed. However, prevailing Re-ID models are usually built upon backbones that manually design for classification. In order to automatically design an effective Re-ID architect...

Full description

Bibliographic Details
Main Authors: Zhou Lei, Kangkang Yang, Kai Jiang, Shengbo Chen
Format: Article
Language:English
Published: MDPI AG 2021-04-01
Series:Algorithms
Subjects:
architecture search
knowledge distillation
person re-identification
dynamic temperature
convolutional network
Online Access:https://www.mdpi.com/1999-4893/14/5/137

Internet

https://www.mdpi.com/1999-4893/14/5/137

Similar Items