Accelerating Image Classification using Feature Map Similarity in Convolutional Neural Networks

Accelerating Image Classification using Feature Map Similarity in Convolutional Neural Networks

Convolutional neural networks (CNNs) have greatly improved image classification performance. However, the extensive time required for classification owing to the large amount of computation involved, makes it unsuitable for application to low-performance devices. To speed up image classification, we...

Full description

Bibliographic Details
Main Authors: Keunyoung Park, Doo-Hyun Kim
Format: Article
Language:English
Published: MDPI AG 2018-12-01
Series:Applied Sciences
Subjects:
image classification
convolutional neural network
feature map
cosine similarity
Online Access:http://www.mdpi.com/2076-3417/9/1/108

Internet

http://www.mdpi.com/2076-3417/9/1/108

Similar Items