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

Maritime surveillance is not only necessary for every country, such as inmaritime safeguarding and fishing controls, but also plays an essential role ininternational fields, such as in rescue support and illegal immigrationcontrol. Most of the existing automatic target recognition (ATR) methodsdirectly send the extracted whole features of SAR ships into one classifier.The classifiers of most methods only assign one feature center to each class.However, the characteristics of SAR ship images, large inner-class variance,and small interclass difference lead to the whole features containing uselesspartial features and a single feature center for each class in the classifierfailing with large inner-class variance. We proposes a SAR ship targetrecognition method via selective feature discrimination and multifeature centerclassifier. The selective feature discrimination automatically finds thesimilar partial features from the most similar interclass image pairs and thedissimilar partial features from the most dissimilar inner-class image pairs.It then provides a loss to enhance these partial features with more interclassseparability. Motivated by divide and conquer, the multifeature centerclassifier assigns multiple learnable feature centers for each ship class. Inthis way, the multifeature centers divide the large inner-class variance intoseveral smaller variances and conquered by combining all feature centers of oneship class. Finally, the probability distribution over all feature centers isconsidered comprehensively to achieve an accurate recognition of SAR shipimages. The ablation experiments and experimental results on OpenSARShip andFUSAR-Ship datasets show that our method has achieved superior recognitionperformance under decreasing training SAR ship samples.

SAR Ship Target Recognition via Selective Feature Discrimination and Multifeature Center Classifier