RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark

TL;DR

This paper introduces the Unit Cycle Resolver to improve angle prediction in weakly supervised rotated object detection, and presents RSAR, the largest rotated SAR dataset, demonstrating enhanced performance over existing methods.

Contribution

The paper proposes the Unit Cycle Resolver to address angle prediction biases and introduces RSAR, a large-scale rotated SAR dataset, advancing weakly supervised SAR object detection.

Findings

UCR improves angle prediction accuracy.

UCR enhances performance of weakly supervised methods.

RSAR dataset enables better SAR object detection benchmarking.

Abstract

Rotated object detection has made significant progress in the optical remote sensing. However, advancements in the Synthetic Aperture Radar (SAR) field are laggard behind, primarily due to the absence of a large-scale dataset. Annotating such a dataset is inefficient and costly. A promising solution is to employ a weakly supervised model (e.g., trained with available horizontal boxes only) to generate pseudo-rotated boxes for reference before manual calibration. Unfortunately, the existing weakly supervised models exhibit limited accuracy in predicting the object's angle. Previous works attempt to enhance angle prediction by using angle resolvers that decouple angles into cosine and sine encodings. In this work, we first reevaluate these resolvers from a unified perspective of dimension mapping and expose that they share the same shortcomings: these methods overlook the unit cycle constraint inherent in these encodings, easily leading to prediction biases. To address this issue, we propose the Unit Cycle Resolver, which incorporates a unit circle constraint loss to improve angle prediction accuracy. Our approach can effectively improve the performance of existing state-of-the-art weakly supervised methods and even surpasses fully supervised models on existing optical benchmarks (i.e., DOTA-v1.0 dataset). With the aid of UCR, we further annotate and introduce RSAR, the largest multi-class rotated SAR object detection dataset to date. Extensive experiments on both RSAR and optical datasets demonstrate that our UCR enhances angle prediction accuracy. Our dataset and code can be found at: https://github.com/zhasion/RSAR.