A Classification-Aware Super-Resolution Framework for Ship Targets in SAR Imagery

TL;DR

This paper introduces a super-resolution framework tailored for SAR imagery that integrates classification objectives to improve both image quality and classification accuracy, addressing limitations of traditional pixel-focused methods.

Contribution

It presents a novel classification-aware super-resolution method that jointly optimizes for image quality and classification performance in SAR imagery.

Findings

Improved super-resolution image quality based on scientific quality indicators.

Enhanced classification accuracy on SAR images.

Joint optimization strategy effectively links super-resolution and classification tasks.

Abstract

High-resolution imagery plays a critical role in improving the performance of visual recognition tasks such as classification, detection, and segmentation. In many domains, including remote sensing and surveillance, low-resolution images can limit the accuracy of automated analysis. To address this, super-resolution (SR) techniques have been widely adopted to attempt to reconstruct high-resolution images from low-resolution inputs. Related traditional approaches focus solely on enhancing image quality based on pixel-level metrics, leaving the relationship between super-resolved image fidelity and downstream classification performance largely underexplored. This raises a key question: can integrating classification objectives directly into the super-resolution process further improve classification accuracy? In this paper, we try to respond to this question by investigating the relationship between super-resolution and classification through the deployment of a specialised algorithmic strategy. We propose a novel methodology that increases the resolution of synthetic aperture radar imagery by optimising loss functions that account for both image quality and classification performance. Our approach improves image quality, as measured by scientifically ascertained image quality indicators, while also enhancing classification accuracy.