Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Zhiqiang, Liu, Yingjie, Sun, Licheng, Yang, Jian, Dong, Hanlin, Lin, Shing-Ho J., Tang, Xuan, Mi, Jinpeng, Jin, Bo, Wei, Xian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.12454
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913648845258752
author Wu, Zhiqiang
Liu, Yingjie
Sun, Licheng
Yang, Jian
Dong, Hanlin
Lin, Shing-Ho J.
Tang, Xuan
Mi, Jinpeng
Jin, Bo
Wei, Xian
author_facet Wu, Zhiqiang
Liu, Yingjie
Sun, Licheng
Yang, Jian
Dong, Hanlin
Lin, Shing-Ho J.
Tang, Xuan
Mi, Jinpeng
Jin, Bo
Wei, Xian
contents Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the transformations under the specific group. However, the presentation or distribution of real-world data rarely conforms to strict rotational equivariance, commonly referred to as Rotational Symmetry-Breaking (RSB) in the system or dataset, making GConv unable to adapt effectively to this phenomenon. Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called $G$-Biases under the group order to break strict group constraints and then achieve a Relaxed Rotational Equivariant Convolution (RREConv). To validate the efficiency of RREConv, we conduct extensive ablation experiments on the discrete rotational group $\mathcal{C}_n$. Experiments demonstrate that the proposed RREConv-based methods achieve excellent performance compared to existing GConv-based methods in both classification and 2D object detection tasks on the natural image datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12454
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Relaxed Rotational Equivariance via $G$-Biases in Vision
Wu, Zhiqiang
Liu, Yingjie
Sun, Licheng
Yang, Jian
Dong, Hanlin
Lin, Shing-Ho J.
Tang, Xuan
Mi, Jinpeng
Jin, Bo
Wei, Xian
Computer Vision and Pattern Recognition
Artificial Intelligence
Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the transformations under the specific group. However, the presentation or distribution of real-world data rarely conforms to strict rotational equivariance, commonly referred to as Rotational Symmetry-Breaking (RSB) in the system or dataset, making GConv unable to adapt effectively to this phenomenon. Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called $G$-Biases under the group order to break strict group constraints and then achieve a Relaxed Rotational Equivariant Convolution (RREConv). To validate the efficiency of RREConv, we conduct extensive ablation experiments on the discrete rotational group $\mathcal{C}_n$. Experiments demonstrate that the proposed RREConv-based methods achieve excellent performance compared to existing GConv-based methods in both classification and 2D object detection tasks on the natural image datasets.
title Relaxed Rotational Equivariance via $G$-Biases in Vision
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.12454