Guided Unsupervised Learning by Subaperture Decomposition for Ocean SAR Image Retrieval

TL;DR

This paper introduces a subaperture decomposition technique to enhance unsupervised learning for ocean SAR image retrieval, significantly improving accuracy and enabling physics-guided retrieval without extensive labeled data.

Contribution

The study presents a novel use of subaperture decomposition to boost unsupervised SAR image retrieval performance, especially with transformer auto-encoders and Doppler centroid data.

Findings

Over 20% improvement in retrieval precision with SD

Enhanced performance using Doppler centroid images

Potential for physics-guided unsupervised algorithms

Abstract

Spaceborne synthetic aperture radar (SAR) can provide accurate images of the ocean surface roughness day-or-night in nearly all weather conditions, being an unique asset for many geophysical applications. Considering the huge amount of data daily acquired by satellites, automated techniques for physical features extraction are needed. Even if supervised deep learning methods attain state-of-the-art results, they require great amount of labeled data, which are difficult and excessively expensive to acquire for ocean SAR imagery. To this end, we use the subaperture decomposition (SD) algorithm to enhance the unsupervised learning retrieval on the ocean surface, empowering ocean researchers to search into large ocean databases. We empirically prove that SD improve the retrieval precision with over 20% for an unsupervised transformer auto-encoder network. Moreover, we show that SD brings important performance boost when Doppler centroid images are used as input data, leading the way to new unsupervised physics guided retrieval algorithms.