# Relaxed Rotational Equivariance via $G$-Biases in Vision

Source: [Relaxed Rotational Equivariance via $G$-Biases in Vision](<https://www.sota2.com/research/paper/68fa769b1e209131cea6e15c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:45:57.319Z

Authors: Zhiqiang Wu, Yingjie Liu, Licheng Sun, Jian Yang, Hanlin Dong, Shing-Ho J. Lin, Xuan Tang, Jinpeng Mi, Bo Jin, Xian Wei

Published: 2024-08-22T14:52:53.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2408.12454>)

[PDF](<https://arxiv.org/pdf/2408.12454.pdf>)
