Litcius/Paper detail

SS R-CNN: Self-Supervised Learning Improving Mask R-CNN for Ship Detection in Remote Sensing Images

Ling Jian, Zhiqi Pu, Lili Zhu, Tiancan Yao, Xijun Liang

2022Remote Sensing31 citationsDOIOpen Access PDF

Abstract

Due to the cost of acquiring and labeling remote sensing images, only a limited number of images with the target objects are obtained and labeled in some practical applications, which severely limits the generalization capability of typical deep learning networks. Self-supervised learning can learn the inherent feature representations of unlabeled instances and is a promising technique for marine ship detection. In this work, we design a more-way CutPaste self-supervised task to train a feature representation network using clean marine surface images with no ships, based on which a two-stage object detection model using Mask R-CNN is improved to detect marine ships. Experimental results show that with a limited number of labeled remote sensing images, the designed model achieves better detection performance than supervised baseline methods in terms of mAP. Particularly, the detection accuracy for small-sized marine ships is evidently improved.

Topics & Concepts

Computer scienceArtificial intelligenceGeneralizationObject detectionPattern recognition (psychology)Feature (linguistics)Representation (politics)Deep learningRemote sensingTask (project management)Feature learningSupervised learningComputer visionArtificial neural networkGeologyMathematicsPhilosophyMathematical analysisPoliticsLinguisticsLawManagementPolitical scienceEconomicsAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning