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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Ying, Chen, Yushi, Yang, Xue, Li, Qingyun, Yan, Junchi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914742653681664
author Zeng, Ying
Chen, Yushi
Yang, Xue
Li, Qingyun
Yan, Junchi
author_facet Zeng, Ying
Chen, Yushi
Yang, Xue
Li, Qingyun
Yan, Junchi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2303_04989
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
Zeng, Ying
Chen, Yushi
Yang, Xue
Li, Qingyun
Yan, Junchi
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2303.04989