ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild

TL;DR

This paper introduces ATRNet-STAR, a large and diverse SAR dataset with over 190,000 samples across 40 vehicle categories, enabling comprehensive benchmarking and advancing research in remote sensing object recognition.

Contribution

The paper presents a new large-scale SAR dataset, ATRNet-STAR, with extensive annotations and evaluations of 15 methods, filling a critical gap in SAR ATR research resources.

Findings

ATRNet-STAR is 10 times larger than MSTAR.

Extensive evaluation reveals strengths and weaknesses of current methods.

Insights and future directions for SAR ATR are discussed.

Abstract

The absence of publicly available, large-scale, high-quality datasets for Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has significantly hindered the application of rapidly advancing deep learning techniques, which hold huge potential to unlock new capabilities in this field. This is primarily because collecting large volumes of diverse target samples from SAR images is prohibitively expensive, largely due to privacy concerns, the characteristics of microwave radar imagery perception, and the need for specialized expertise in data annotation. Throughout the history of SAR ATR research, there have been only a number of small datasets, mainly including targets like ships, airplanes, buildings, etc. There is only one vehicle dataset MSTAR collected in the 1990s, which has been a valuable source for SAR ATR. To fill this gap, this paper introduces a large-scale, new dataset named ATRNet-STAR with 40 different vehicle categories collected under various realistic imaging conditions and scenes. It marks a substantial advancement in dataset scale and diversity, comprising over 190,000 well-annotated samples, 10 times larger than its predecessor, the famous MSTAR. Building such a large dataset is a challenging task, and the data collection scheme will be detailed. Secondly, we illustrate the value of ATRNet-STAR via extensively evaluating the performance of 15 representative methods with 7 different experimental settings on challenging classification and detection benchmarks derived from the dataset. Finally, based on our extensive experiments, we identify valuable insights for SAR ATR and discuss potential future research directions in this field. We hope that the scale, diversity, and benchmark of ATRNet-STAR can significantly facilitate the advancement of SAR ATR.