Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification

作者：

Highlights：

• We propose to encode shareable and discriminative information in feature learning.

• Two exemplar selection methods are proposed to select effective training data.

• We build a hierarchical learning scheme to capture multiple visual level information.

• Our DDSFL outperforms most of the existing features.

• DDSFL features show great complementary effect to Caffe features.

摘要

Highlights•We propose to encode shareable and discriminative information in feature learning.•Two exemplar selection methods are proposed to select effective training data.•We build a hierarchical learning scheme to capture multiple visual level information.•Our DDSFL outperforms most of the existing features.•DDSFL features show great complementary effect to Caffe features.

论文关键词：Deep feature learning,Information sharing,Discriminative training,Scene image classification

论文评审过程：Received 1 October 2014, Revised 25 January 2015, Accepted 3 February 2015, Available online 16 February 2015, Version of Record 17 June 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.02.003