LAUSR

Oriented object detection in remote sensing images has attracted significant attention, as rotated bounding boxes can more accurately fit targets with arbitrary orientations. However, existing oriented detection models still struggle with challenges such as angle regression instability and ambiguity caused by angle periodicity and edge exchange, which hinder their effectiveness in practical remote sensing applications. To address these issues, we propose a one-stage heatmap-based rotated object detector, named RANet. In this framework, we introduce correlated vector labels to simultaneously tackle the periodicity of angle problem and the exchange of edges issue. Furthermore, RANet leverages pixel-level features around extreme points to perform unbiased coordinate estimation through a Taylor expansion, improving localization accuracy. To enhance training stability and performance, we design a swap vector loss to optimize the angular regression for objects with varying aspect ratios, and a continuous focal loss to maintain heatmap smoothness. Extensive experiments on multiple datasets demonstrate that our method achieves superior recall and precision compared to state-of-the-art approaches.