Network generating network for multi-scale image classification

Hang Dong; Liping Xiao; Longjian Cong; Bin Zhou

doi:10.1117/12.2671561

16 March 2023 Network generating network for multi-scale image classification

Hang Dong, Liping Xiao, Longjian Cong, Bin Zhou

Proceedings Volume 12593, Second Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum (AIBDF 2022); 125931E (2023) https://doi.org/10.1117/12.2671561
Event: 2nd Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum (AIBDF 2022), 2022, Guangzhou, China

Abstract

Features extracted by the neural network do not have scale invariance, which makes multi-scale image recognition and classification a difficult problem. Recent studies have proposed many new ways to solve this problem, such as feature fusion, sensor field transformation, etc. However, none of them essentially solve the problem that the neural network does not have scale invariance. In this paper, we propose a network generating network (NGN) architecture and design the NGNResNet network, which is an improved version of the ResNet network. The network can identify images at three scales simultaneously and has scale invariance. The experimental results show that the NGN structure helps us to improve the classification accuracy of small-scale images by about 10 percentage points, and helps to improve the performance of the network in the face of small targets.

Citation Download Citation

Hang Dong, Liping Xiao, Longjian Cong, and Bin Zhou "Network generating network for multi-scale image classification", Proc. SPIE 12593, Second Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum (AIBDF 2022), 125931E (16 March 2023); https://doi.org/10.1117/12.2671561

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available