Continual learning for scene classification of high resolution remote sensing images

Jiangbo Xi; Ziyun Yan; Wandong Jiang; Yaobing Xiang; Dashuai Xie

doi:10.1117/12.2605919

1 November 2021 Continual learning for scene classification of high resolution remote sensing images

Jiangbo Xi, Ziyun Yan, Wandong Jiang, Yaobing Xiang, Dashuai Xie

Proceedings Volume 12057, Twelfth International Conference on Information Optics and Photonics; 120572I (2021) https://doi.org/10.1117/12.2605919
Event: Twelfth International Conference on Information Optics and Photonics, 2021, Xi'an, China

Abstract

Deep learning has achieved great success in optical image classification tasks including high resolution remote sensing image classification and segmentation. However, recent deep learning models usually use static training methods, therefore, long time and huge data are needed during training. The traditional end-to-end deep learning models are difficult to achieve incremental learning, which is learning new knowledge without forgetting learned knowledge. The continual learning was recently used to overcome this catastrophic forgetting problem. It is mainly on continual updating and optimizing the learning model to learn knowledge incrementally. In this paper, we proposed a continual learning model for the classification of high resolution remote sensing image scenes. It is a memory consolidation method using fixed representation. Fixed representation learning divides the network into three parts to be trained separately to adapt for continual learning scenarios, and the memory consolidation method solves the catastrophic forgetting problem through distillation loss, optimal sample replay, and classification layer correction. We compared the proposed method with the existing continual learning methods elastic weight consolidation (EWC), and learning without forgetting (LWF) methods, the experimental results show that the proposed method is effective for remote sensing scenarios classification, and has good performance on suppressing catastrophic forgetting. We also comprehensively analyzed the proposed method in multiple angles, and it is seen that there is still room for optimizing the proposed method in terms of model architecture, loss value, and training method.

Citation Download Citation

Jiangbo Xi, Ziyun Yan, Wandong Jiang, Yaobing Xiang, and Dashuai Xie "Continual learning for scene classification of high resolution remote sensing images", Proc. SPIE 12057, Twelfth International Conference on Information Optics and Photonics, 120572I (1 November 2021); https://doi.org/10.1117/12.2605919

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
17 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Remote sensing

Data modeling

Statistical modeling

Performance modeling

Scene classification

Image classification

Image resolution

Show All Keywords

Keywords/Phrases

Search In:

Publication Years