Measuring the Impact of Rotation Equivariance on Aerial Object Detection

TL;DR

This paper investigates the importance of strict rotation equivariance in aerial object detection by implementing a novel network architecture, MessDet, which outperforms existing methods on multiple datasets with fewer parameters.

Contribution

It introduces a strictly rotation-equivariant backbone and a multi-branch head network, achieving state-of-the-art results with reduced parameters in aerial object detection.

Findings

Strict rotation equivariance improves detection accuracy.

The proposed MessDet outperforms existing methods on DOTA and DIOR-R datasets.

Parameter reduction is achieved without sacrificing performance.

Abstract

Due to the arbitrary orientation of objects in aerial images, rotation equivariance is a critical property for aerial object detectors. However, recent studies on rotation-equivariant aerial object detection remain scarce. Most detectors rely on data augmentation to enable models to learn approximately rotation-equivariant features. A few detectors have constructed rotation-equivariant networks, but due to the breaking of strict rotation equivariance by typical downsampling processes, these networks only achieve approximately rotation-equivariant backbones. Whether strict rotation equivariance is necessary for aerial image object detection remains an open question. In this paper, we implement a strictly rotation-equivariant backbone and neck network with a more advanced network structure and compare it with approximately rotation-equivariant networks to quantitatively measure the impact of rotation equivariance on the performance of aerial image detectors. Additionally, leveraging the inherently grouped nature of rotation-equivariant features, we propose a multi-branch head network that reduces the parameter count while improving detection accuracy. Based on the aforementioned improvements, this study proposes the Multi-branch head rotation-equivariant single-stage Detector (MessDet), which achieves state-of-the-art performance on the challenging aerial image datasets DOTA-v1.0, DOTA-v1.5 and DIOR-R with an exceptionally low parameter count.