Abstract
The scarcity of open SAR (Synthetic Aperture Radars) imagery databases (especially the labeled ones) and sparsity of pre-trained neural networks lead to the need for heavy data generation, augmentation, or transfer learning usage. This paper described the characteristics of SAR imagery, the limitations related to it, and a small set of available databases. Comprehensive data augmentation methods for training Neural Networks were presented, and a novel filter-based method was proposed. The new method limits the effect of the speckle noise, which is very high-level in SAR imagery. The improvement in the dataset could be clearly registered in the loss value functions. The main advantage comes from more developed feature detectors for filter-based training, which is shown in the layer-wise feature analysis. The author attached the trained neural networks for open use. This provides quicker CNN-based solutions implementation.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference37 articles.
1. Deep transformers and convolutional neural network in identifying DNA N6-methyladenine sites in cross-species genomes
2. ImageNethttps://www.image-net.org/
3. COCO—Common Objects in Contexthttps://cocodataset.org/#home
4. CIFAR-10 and CIFAR-100 Datasetshttp://www.cs.toronto.edu/~kriz/cifar.html
5. GitHub—v7labs/COVID-19-Xray-Dataset: 12000+ Manually Drawn Pixel-Level Lung Segmentations, with and without COVIDhttps://github.com/v7labs/covid-19-xray-dataset
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献