Synthetical application of multi-feature map detection and multi-branch convolution

Synthetical application of multi-feature map detection and multi-branch convolution

Abstract Two methods for improving the detection performance of neural networks are introduced in this paper, multi-feature map detection and multi-branch convolution structure. The former is to analyze the features of each convolution layer in the network separately, because these features have dif...

Full description

Bibliographic Details
Main Authors: Jin Chen, Rong Liu, Ying Tong, Hanling Wu
Format: Article
Language:English
Published: SpringerOpen 2019-05-01
Series:EURASIP Journal on Wireless Communications and Networking
Subjects:
Multi-branch convolution
Multi-feature map detection
Receptive field block (RFB) net
Single shot multibox detector (SSD)
Online Access:http://link.springer.com/article/10.1186/s13638-019-1444-y

Internet

http://link.springer.com/article/10.1186/s13638-019-1444-y

Similar Items