Anchor-free Oriented Proposal Generator for Object Detection

Abstract

Oriented object detection is a practical and challenging task in remote sensing image interpretation. Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them. However, the horizontal boxes are inclined to get small Intersection-over-Unions (IoUs) with ground truths, which may have some undesirable effects, such as introducing redundant noise, mismatching with ground truths, detracting from the robustness of detectors, etc. In this paper, we propose a novel Anchor-free Oriented Proposal Generator (AOPG) that abandons horizontal box-related operations from the network architecture. AOPG first produces coarse oriented boxes by a Coarse Location Module (CLM) in an anchor-free manner and then refines them into high-quality oriented proposals. After AOPG, we apply a Fast R-CNN head to produce the final detection results. Furthermore, the shortage of large-scale datasets is also a hindrance to the development of oriented object detection. To alleviate the data insufficiency, we release a new dataset on the basis of our DIOR dataset and name it DIOR-R. Massive experiments demonstrate the effectiveness of AOPG. Particularly, without bells and whistles, we achieve the accuracy of 64.41%, 75.24% and 96.22% mAP on the DIOR-R, DOTA and HRSC2016 datasets respectively. Code and models are available at https://github.com/jbwang1997/AOPG.

References in corpus (4)

• MMDetection: Open MMLab Detection Toolbox and Benchmark
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• Learning Modulated Loss for Rotated Object Detection
• Dynamic Anchor Learning for Arbitrary-Oriented Object Detection

Cited by in corpus (14)

• Towards Large-Scale Small Object Detection: Survey and Benchmarks
• ${\mathbf{C}}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection
• ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
• Fewer is More: Efficient Object Detection in Large Aerial Images
• Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching
• Oriented object detection in optical remote sensing images using deep learning: a survey
• Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
• RQFormer: Rotated Query Transformer for End-to-End Oriented Object Detection
• Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images
• Learning to Detect Open Carry and Concealed Object with 77GHz Radar
• EARL: An Elliptical Distribution aided Adaptive Rotation Label Assignment for Oriented Object Detection in Remote Sensing Images
• Multi-Grained Angle Representation for Remote Sensing Object Detection
• Semi-supervised Open-World Object Detection
• Oriented RepPoints for Aerial Object Detection