Back to Search Start Over

SBDet: A Symmetry-Breaking Object Detector via Relaxed Rotation-Equivariance

Authors :
Wu, Zhiqiang
Liu, Yingjie
Dong, Hanlin
Tang, Xuan
Yang, Jian
Jin, Bo
Chen, Mingsong
Wei, Xian
Publication Year :
2024

Abstract

Introducing Group Equivariant Convolution (GConv) empowers models to explore symmetries hidden in visual data, improving their performance. However, in real-world scenarios, objects or scenes often exhibit perturbations of a symmetric system, specifically a deviation from a symmetric architecture, which can be characterized by a non-trivial action of a symmetry group, known as Symmetry-Breaking. Traditional GConv methods are limited by the strict operation rules in the group space, only ensuring features remain strictly equivariant under limited group transformations, making it difficult to adapt to Symmetry-Breaking or non-rigid transformations. Motivated by this, we introduce a novel Relaxed Rotation GConv (R2GConv) with our defined Relaxed Rotation-Equivariant group $\mathbf{R}_4$. Furthermore, we propose a Relaxed Rotation-Equivariant Network (R2Net) as the backbone and further develop the Symmetry-Breaking Object Detector (SBDet) for 2D object detection built upon it. Experiments demonstrate the effectiveness of our proposed R2GConv in natural image classification tasks, and SBDet achieves excellent performance in object detection tasks with improved generalization capabilities and robustness.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2408.11760
Document Type :
Working Paper