Remote sensing image scene classification based on transfer learning and Swin transformer mode

Yating Qiao; Jianwei Ge; Yadong Zhang; Yantong Ling

doi:10.1117/12.3010458

15 November 2023 Remote sensing image scene classification based on transfer learning and Swin transformer mode

Yating Qiao, Jianwei Ge, Yadong Zhang, Yantong Ling

Proceedings Volume 12815, International Conference on Remote Sensing, Mapping, and Geographic Systems (RSMG 2023); 128150S (2023) https://doi.org/10.1117/12.3010458
Event: International Conference on Remote Sensing, Mapping, and Geographic Systems (RSMG 2023), 2023, Kaifeng, China

Abstract

Remote sensing image scene has the characteristics of complex background, large regional, seasonal and scale differences of similar scenes. This paper proposes a remote sensing image scene classification method based on migration learning and Swin Transformer model. The Swin-T model is pre-trained using ImageNet datasets to obtain the weight parameters of the pre-trained model, and then the migration learning method is used. Six remote sensing im-age datasets, including UCM, AID, NWPU, GID, NaSC-TG2 and SenseEarth Classify, are validated. The verification results showed that the overall classification accuracy was 99. 99%, 96.80%, 95.20%, 96.63%, 99.35% and 97. 09% respectively, and good classification results were obtained.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yating Qiao, Jianwei Ge, Yadong Zhang, and Yantong Ling "Remote sensing image scene classification based on transfer learning and Swin transformer mode", Proc. SPIE 12815, International Conference on Remote Sensing, Mapping, and Geographic Systems (RSMG 2023), 128150S (15 November 2023); https://doi.org/10.1117/12.3010458

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