ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection

Abstract

Existing oriented object detection methods commonly use metric AP${}_{50}$ to measure the performance of the model. We argue that AP${}_{50}$ is inherently unsuitable for oriented object detection due to its large tolerance in angle deviation. Therefore, we advocate using high-precision metric, e.g. AP${}_{75}$, to measure the performance of models. In this paper, we propose an Aspect Ratio Sensitive Oriented Object Detector with Transformer, termed ARS-DETR, which exhibits a competitive performance in high-precision oriented object detection. Specifically, a new angle classification method, calling Aspect Ratio aware Circle Smooth Label (AR-CSL), is proposed to smooth the angle label in a more reasonable way and discard the hyperparameter that introduced by previous work (e.g. CSL). Then, a rotated deformable attention module is designed to rotate the sampling points with the corresponding angles and eliminate the misalignment between region features and sampling points. Moreover, a dynamic weight coefficient according to the aspect ratio is adopted to calculate the angle loss. Comprehensive experiments on several challenging datasets show that our method achieves competitive performance on the high-precision oriented object detection task.

15 pages, 13 figures, 13 tables, the source code is available at https://github.com/httle/ARS-DETR

References in corpus (10)

• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• Arbitrary-Oriented Scene Text Detection via Rotation Proposals
• Gliding vertex on the horizontal bounding box for multi-oriented object detection
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• Anchor-free Oriented Proposal Generator for Object Detection
• DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
• MMRotate: A Rotated Object Detection Benchmark using PyTorch
• Position Detection and Direction Prediction for Arbitrary-Oriented Ships via Multitask Rotation Region Convolutional Neural Network
• Oriented Object Detection with Transformer
• Multi-Grained Angle Representation for Remote Sensing Object Detection

Cited by in corpus (3)

• Oriented object detection in optical remote sensing images using deep learning: a survey
• RQFormer: Rotated Query Transformer for End-to-End Oriented Object Detection
• DTKDP: A Dual Teacher Knowledge Distillation and Pruning Framework for Lightweight Oriented SAR Ship Detection