Improved Dc Estimation For Jpeg Compression Via Convex Relaxation

Unlike traditional opto-electronic satellite imaging, Sythetic Aperture Radar (SAR) allows for remote sensing applications to operate under all weather conditions. This makes it uniquely valuable for detecting ships/vessels involved in illegal, unreported, and unregulated (IUU) fishing. While recent work has shown significant improvement on this domain, detecting small objects using noisy point annotations remains an unexplored area. in order to meet the unique challenges of this problem we propose a progressive training methodology which utilizes two different spatial sampling strategies. Firstly, we use stochastic sampling of background points to reduce the impact of class imbalance and missing labels, and secondly during the refinement stage we use hard negative sampling to improve the model. Experimental results on the challenging xView3 dataset show that our method out-performs conventional small object localization methods in a large noisy dataset of SAR images. Source code for our method can be found at: https://github.com/manupillai308/DeepSAR