Litcius/Paper detail

Imbalanced High-Resolution SAR Ship Recognition Method Based on a Lightweight CNN

Ying Zhang, Zhiyong Lei, Hui Yu, Long Zhuang

2021IEEE Geoscience and Remote Sensing Letters37 citationsDOI

Abstract

Convolutional neural network (CNN)-based methods have become the mainstream in radar ship recognition. However, these methods suffer from two common problems. First, the training samples consist largely of common ship types, giving them an overwhelming numerical advantage over rare ship types. As a result, CNN-based recognition algorithms fail to classify rare ship types correctly. Second, huge high-resolution slices result in heavy computational burdens. To solve the first problem, namely, the class imbalance problem, this letter proposes a CNN training method that combines deep metric learning (DML) with gradually balanced sampling. DML obtains the center of each class in the feature space and performs clustering equally. Gradually balanced sampling adopts a smooth transition from instance-aware resampling to class-aware resampling to improve the recognition rate drop caused by traditional resampling methods. As for the second problem, to reduce the computational complexity of high-resolution synthetic aperture radar (SAR) images, a lightweight CNN is also proposed.

Topics & Concepts

Computer scienceArtificial intelligenceConvolutional neural networkResamplingSynthetic aperture radarCluster analysisPattern recognition (psychology)Radar imagingFeature extractionDeep learningFeature (linguistics)Class (philosophy)RadarComputer visionLinguisticsPhilosophyTelecommunicationsAnomaly Detection Techniques and ApplicationsAdvanced SAR Imaging TechniquesForensic Anthropology and Bioarchaeology Studies
Imbalanced High-Resolution SAR Ship Recognition Method Based on a Lightweight CNN | Litcius