paper-with-me

홈 › Papers

Quaternion Convolutional Neural Networks

2019-03-02 · ECCV 2018 9 · Xuanyu Zhu, Yi Xu, Hongteng Xu, Changjian Chen

Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years. However, the extensions of the neural network models in other number fields and their potential applications are not fully-investigated yet. Focusing on color images, which can be naturally represented as quaternion matrices, we propose a quaternion convolutional neural network (QCNN) model to obtain more representative features. In particular, we redesign the basic modules like convolution layer and fully-connected layer in the quaternion domain, which can be used to establish fully-quaternion convolutional neural networks. Moreover, these modules are compatible with almost all deep learning techniques and can be plugged into traditional CNNs easily. We test our QCNN models in both color image classification and denoising tasks. Experimental results show that they outperform the real-valued CNNs with same structures.

📄 PDF Abstract BibTeX arXiv:1903.00658

Code (2)

XYZ387/QuaternionCNN_Keras tf
jorisweeda/quaternion-convolutional-neural-networks pytorch

Tasks

Denoisingimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Quaternion-Valued Convolutional Neural Network Applied for Acute Lymphoblastic Leukemia Diagnosis

2021-12-13 · Marco Aurélio Granero, Cristhian Xavier Hernández, Marcos Eduardo Valle

The field of neural networks has seen significant advances in recent years with the development of deep and convolutional neural networks. Although many of the current works address real-valued models, recent studies rev…

Quaternion Matrix Completion Using Untrained Quaternion Convolutional Neural Network for Color Image Inpainting

2023-04-30 · Jifei Miao, Kit Ian Kou, Liqiao Yang, Juan Han

The use of quaternions as a novel tool for color image representation has yielded impressive results in color image processing. By considering the color image as a unified entity rather than separate color space componen…

Image InpaintingMatrix Completion

Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition

2018-06-20 · Titouan Parcollet, Ying Zhang, Mohamed Morchid, Chiheb Trabelsi 외

Recently, the connectionist temporal classification (CTC) model coupled with recurrent (RNN) or convolutional neural networks (CNN), made it easier to train speech recognition systems in an end-to-end fashion. However in…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Phoneme Recognitionspeech-recognition+1

Statistical Analysis of the Impact of Quaternion Components in Convolutional Neural Networks

2024-08-29 · Gerardo Altamirano-Gómez, Carlos Gershenson

In recent years, several models using Quaternion-Valued Convolutional Neural Networks (QCNNs) for different problems have been proposed. Although the definition of the quaternion convolution layer is the same, there are …

image-classificationImage Classification

Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events

2018-12-17 · Danilo Comminiello, Marco Lella, Simone Scardapane, Aurelio Uncini

Learning from data in the quaternion domain enables us to exploit internal dependencies of 4D signals and treating them as a single entity. One of the models that perfectly suits with quaternion-valued data processing is…

Event DetectionSound Event Detection