Improving the Separability of Deep Features with Discriminative Convolution Filters for RSI Classification

Improving the Separability of Deep Features with Discriminative Convolution Filters for RSI Classification

The extraction of activation vectors (or deep features) from the fully connected layers of a convolutional neural network (CNN) model is widely used for remote sensing image (RSI) representation. In this study, we propose to learn discriminative convolution filter (DCF) based on class-specific separ...

Full description

Bibliographic Details
Main Authors: Na Liu, Xiankai Lu, Lihong Wan, Hong Huo, Tao Fang
Format: Article
Language:English
Published: MDPI AG 2018-03-01
Series:ISPRS International Journal of Geo-Information
Subjects:
convolutional neural network
discriminative convolution filter
image classification
remote sensing
Online Access:http://www.mdpi.com/2220-9964/7/3/95

Internet

http://www.mdpi.com/2220-9964/7/3/95

Similar Items