跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 27 天前AI 評分33

Quaternion Approximate Networks:提升圖像分類與定向目標檢測

Quaternion Approximate Networks for Enhanced Image Classification and Oriented Object Detection

AI 導讀

QUAN 提出一種四元數深度學習框架,以實數運算近似四元數卷積,實現具旋轉等變性的圖像分類與目標檢測。框架引入 Independent Quaternion Batch Normalization(IQBN),並以自訂 CUDA kernels 提升實作效率。

正文

Published on Oct 27

·

Submitted by

Bryce

on Oct 28

Authors:

Abstract

QUAN is a quaternion-based deep learning framework that approximates quaternion convolution with real-valued operations to achieve rotation-equivariant image classification and object detection with improved efficiency.

This paper introduces Quaternion Approximate Networks (QUAN), a novel deep learning framework that leverages quaternion algebra for rotation equivariant image classification and object detection. Unlike conventional quaternion neural networks attempting to operate entirely in the quaternion domain, QUAN approximates quaternion convolution through Hamilton product decomposition using real-valued operations. This approach preserves geometric properties while enabling efficient implementation with custom CUDA kernels. We introduce Independent Quaternion Batch Normalization (IQBN) for training stability and extend quaternion operations to spatial attention mechanisms. QUAN is evaluated on image classification (CIFAR-10/100, ImageNet), object detection (COCO, DOTA), and robotic perception tasks. In classification tasks, QUAN achieves higher accuracy with fewer parameters and faster convergence compared to existing convolution and quaternion-based models. For objection detection, QUAN demonstrates improved parameter efficiency and rotation handling over standard Convolutional Neural Networks (CNNs) while establishing the SOTA for quaternion CNNs in this downstream task. These results highlight its potential for deployment in resource-constrained robotic systems requiring rotation-aware perception and application in other domains. Code: https://cwru-aism.github.io/ QUANpaper/

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2509.05512

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.05512 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.05512 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.05512 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co