Histogram Layers for Synthetic Aperture Sonar Imagery

Abstract

Synthetic aperture sonar (SAS) imagery is crucial for several applications, including target recognition and environmental segmentation. Deep learning models have led to much success in SAS analysis; however, the features extracted by these approaches may not be suitable for capturing certain textural information. To address this problem, we present a novel application of histogram layers on SAS imagery. The addition of histogram layer(s) within the deep learning models improved performance by incorporating statistical texture information on both synthetic and real-world datasets.

arXiv comment7 pages, 9 Figures, Accepted to IEEE International Conference on Machine Learning and Applications (ICMLA) 2022

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
• Histogram Layers for Texture Analysis
• Iterative, Deep Synthetic Aperture Sonar Image Segmentation
• Comparison of Possibilistic Fuzzy Local Information C-Means and Possibilistic K-Nearest Neighbors for Synthetic Aperture Sonar Image Segmentation
• Differentiable Histogram with Hard-Binning
• Image-to-Height Domain Translation for Synthetic Aperture Sonar