Deep linear discriminant analysis on fisher networks: A hybrid architecture for person re-identification

作者：

Highlights：

• A hybrid architecture that combines Fisher vectors and deep neural networks.

• An end-to-end training with linear discriminant analysis as objective.

• Deep features are linearly separable and class separability is maximally preserved.

摘要

Highlights•A hybrid architecture that combines Fisher vectors and deep neural networks.•An end-to-end training with linear discriminant analysis as objective.•Deep features are linearly separable and class separability is maximally preserved.

论文关键词：Linear discriminant analysis,Deep Fisher networks,Person re-identification

论文评审过程：Received 25 July 2016, Revised 16 November 2016, Accepted 21 December 2016, Available online 24 December 2016, Version of Record 6 January 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.12.022