Rollable Latent Space for Azimuth Invariant SAR Target Recognition

TL;DR

This paper introduces a rollable latent space (RLS) for SAR target recognition that models 3D rotations, enabling view-invariant recognition and data augmentation, significantly improving accuracy with limited labeled data.

Contribution

The paper presents a novel RLS that aligns latent features with 3D rotations, enhancing azimuth invariance and data augmentation in SAR target recognition.

Findings

RLS-based classifier with augmentation improves accuracy by 30%.

RLS enables inference of features across different views.

Enhanced recognition performance with limited labeled data.

Abstract

This paper proposes rollable latent space (RLS) for an azimuth invariant synthetic aperture radar (SAR) target recognition. Scarce labeled data and limited viewing direction are critical issues in SAR target recognition.The RLS is a designed space in which rolling of latent features corresponds to 3D rotation of an object. Thus latent features of an arbitrary view can be inferred using those of different views. This characteristic further enables us to augment data from limited viewing in RLS. RLS-based classifiers with and without data augmentation and a conventional classifier trained with target front shots are evaluated over untrained target back shots. Results show that the RLS-based classifier with augmentation improves an accuracy by 30% compared to the conventional classifier.