English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Synthetic aperture radar (SAR) imaging technology is commonly used to provide24-hour all-weather earth observation. However, it still has some drawbacks inSAR target classification, especially in fine-grained classification ofaircraft: aircrafts in SAR images have large intra-class diversity andinter-class similarity; the number of effective samples is insufficient andit's hard to annotate. To address these issues, this article proposes a novelmulti-modal self-supervised network (MS-Net) for fine-grained classification ofaircraft. Firstly, in order to entirely exploit the potential of multi-modalinformation, a two-sided path feature extraction network (TSFE-N) isconstructed to enhance the image feature of the target and obtain the domainknowledge feature of text mode. Secondly, a contrastive self-supervisedlearning (CSSL) framework is employed to effectively learn usefullabel-independent feature from unbalanced data, a similarity per-ception loss(SPloss) is proposed to avoid network overfitting. Finally, TSFE-N is used asthe encoder of CSSL to obtain the classification results. Through a largenumber of experiments, our MS-Net can effectively reduce the difficulty ofclassifying similar types of aircrafts. In the case of no label, the proposedalgorithm achieves an accuracy of 88.46% for 17 types of air-craftclassification task, which has pioneering significance in the field offine-grained classification of aircraft in SAR images.

MS-Net: A Multi-modal Self-supervised Network for Fine-Grained Classification of Aircraft in SAR Images