VS-LSDet: A Multiscale Ship Detector for Spaceborne SAR Images Based on Visual Saliency and Lightweight CNN

Recently, deep learning-based methods for synthetic aperture radar (SAR) ship detection have made remarkable advancements. However, most existing methods primarily focus on achieving high detection accuracy by employing complex models, leading to an increase in computational costs. In addition, some methods do not adequately consider the impact of speckle noise interference. To address these challenges, we propose a multiscale ship detector, called visual saliency-lightweight ship detector (VS-LSDet), utilizing visual saliency and lightweight convolutional neural network. First, a visual saliency enhancement module is proposed as a preprocessing step to visually highlight the ships and weaken the impact of speckle noise in the image. Second, a lightweight backbone called ghost-shuffle net (GSNet) is designed. We introduce two types of ghost-shuffle blocks as basic convolution blocks by introducing ghost convolution to reduce the model complexity and channel shuffle operation to enhance the representation ability of the feature map. Then, we propose a multishape dilated convolution block incorporated into GSNet to enlarge its receptive fields, further improving the detector's performance. Finally, a hybrid attention module (HyAM) is proposed, it leverages both spatial and channel information within the feature map. HyAM can emphasize ship-related features while suppressing irrelevant features from the background in the feature map. Experimental results on public SAR ship datasets demonstrate that, compared to other ship detection methods, VS-LSDet achieves higher detection accuracy with lower model complexity. Specifically, on the SSDD dataset, the AP value of VS-LSDet is 97.51%, with 2.53 M parameters and 6.21 GFLOPs.