RMK RetinaNet: Rotated Multi-Kernel RetinaNet for Robust Oriented Object Detection in Remote Sensing Imagery

TL;DR

This paper introduces RMK RetinaNet, a novel rotated object detection framework that enhances feature extraction, contextual modeling, and angle regression to improve robustness in remote sensing imagery.

Contribution

The paper proposes a comprehensive architecture with multi-scale feature extraction, contextual attention, and stable angle regression for improved rotated object detection.

Findings

Achieves performance comparable to state-of-the-art detectors

Improves robustness in multi-scale and multi-orientation scenarios

Effective in remote sensing imagery datasets

Abstract

Rotated object detection in remote sensing imagery is hindered by three major bottlenecks: non-adaptive receptive field utilization, inadequate long-range multi-scale feature fusion, and discontinuities in angle regression. To address these issues, we propose Rotated Multi-Kernel RetinaNet (RMK RetinaNet). First, we design a Multi-Scale Kernel (MSK) Block to strengthen adaptive multi-scale feature extraction. Second, we incorporate a Multi-Directional Contextual Anchor Attention (MDCAA) mechanism into the feature pyramid to enhance contextual modeling across scales and orientations. Third, we introduce a Bottom-up Path to preserve fine-grained spatial details that are often degraded during downsampling. Finally, we develop an Euler Angle Encoding Module (EAEM) to enable continuous and stable angle regression. Extensive experiments on DOTA-v1.0, HRSC2016, and UCAS-AOD show that RMK RetinaNet achieves performance comparable to state-of-the-art rotated object detectors while improving robustness in multi-scale and multi-orientation scenarios.