Showing 1-25 of 3,068 resultsfor "Index Terms":Group Convolution
"Index Terms":Group Convolution
- Sort
Get notified when new research is published matching your search criteria.
Sort By
Results
In this paper we review mathematical models and methods to digital signal processing and investigate some new problems which are connected with noncommutativity of corresponding algebraic structures. Most considerations relate to the theory of digital signal processing from group theoretic perspective.Show More
Dynamically Mixed Group Convolution to Lighten Convolution Operation
2021 4th International Conference on Artificial Intelligence and Big Data (ICAIBD)
Year: 2021 | Conference Paper |
Cited by: Papers (3)
Convolution operation is the most significant component in convolution neural networks (CNNs). However, the high computation cost limits its application on mobiles and embedded devices. To address this problem, in this paper, we develop a dynamically mixed group convolution operation (DMGConv) to lighten convolution operation. It consists of three mixed primary groups, and each primary group inclu...Show More
Application and Improvement of Convolution Operation in Image Restoration
2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC )
Year: 2022 | Conference Paper |
As a new concept and method proposed in the field of neural network, deep learning is introduced into machine learning, which promotes the rapid development of artificial intelligence and provides new ideas for image processing. One of the most representative algorithms is convolutional neural network. As the most important part of convolutional neural network, convolution can effectively extract ...Show More
A Dynamic Group Equivariant Convolutional Networks for Medical Image Analysis
2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Year: 2020 | Conference Paper |
Cited by: Papers (6)
Group equivariant Convolutional Neural Networks (G-CNNs) has led to big empirical success in the medical domain, one fundamental assumption is that equivariance provides a powerful inductive bias for medical images. By leveraging concepts from group representation theory, we can generalize vanilla Convolutional Neural Networks (CNNs) to G-CNN. Currently, although embedding an arbitrary equivarianc...Show More
Efficient Temporal-Spatial Feature Grouping For Video Action Recognition
2020 IEEE International Conference on Image Processing (ICIP)
Year: 2020 | Conference Paper |
Cited by: Papers (4)
Temporal information plays an important role in action recognition. Recently, 3D CNN is widely used in extracting temporal features from videos. Compared to 2D CNN, 3D CNN has more parameters and brings heavy computation burden. It is necessary to improve the efficiency of action recognition. In this paper, inspired by group convolution and convolution kernel decomposition, we propose a novel modu...Show More
An Efficient Accelerator with Winograd for Novel Convolutional Neural Networks
2022 5th International Conference on Circuits, Systems and Simulation (ICCSS)
Year: 2022 | Conference Paper |
Cited by: Papers (1)
In recent years, the current trend of Convolutional Neural Networks (CNNs) is toward lower computational cost to achieve lightweight. In lightweight convolutional neural networks, the depthwise separable convolution (DSC) is becoming the mainstream method. But in DSC, the pointwise convolution (PWC) with $1\times 1$ filters still has abundant parameters and computation. In this paper, an more effi...Show More
3D EMSU‐Net: A framework for automatic segmentation of brain tumors
Luyi Qiu;Ji Geng;Yiling Zhang;Chao Zhang;Dongjie He;Lingling Gao
2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP)
Year: 2021 | Conference Paper |
Cited by: Papers (1)
Glioma is the most common tumor in the brain’s central nerve cells, which is extremely dangerous clinically. Glioma’s accurate surgical localization and diagnosis both rely on the segmentation result of the tumor area in brain Magnetic Resonance Imaging (MRI) images. Recently, deep learning methods have been widely used in the tasks of semantic segmentation of brain tumor images. However, traditio...Show More
A Computationally Efficient Neural Network For Faster Image Classification
2018 IEEE Symposium Series on Computational Intelligence (SSCI)
Year: 2018 | Conference Paper |
Deep Convolutional Neural Networks have led to series of breakthroughs in image classification. With increasing demand to run DCNN based models on mobile platforms with minimal computing capabilities and lesser storage space, the challenge is optimizing those DCNN models for lesser computation and smaller memory footprint. This paper presents a highly efficient and modularized Deep Neural Network ...Show More
GRSiamFC: Group Residual Convolutional Siamese Networks for Object Tracking
2021 International Conference on Control, Automation and Information Sciences (ICCAIS)
Year: 2021 | Conference Paper |
Visual tracking has seen considerable success with fully convolutional Siamese networks (SiamFC). However, the features extracted by SiamFC are redundant in practical applications. Most of the feature channels are ineffective or even serve as noise, which adversely affects tracking performance. The convolutional kernels tend to converge during the training phase of SiamFC, thereby the output featu...Show More
Characterization and Design of Generalized Convolutional Neural Network
2019 53rd Annual Conference on Information Sciences and Systems (CISS)
Year: 2019 | Conference Paper |
The group convolution and representation theory give a strong support for generalized convolutional neural network. The generalized convolutional neural network (G-CNN) has been applied to learning problems and achieved the state-of-art performance. But a theoretical support for details of network architecture design is still lacking. In this work, we first analyze the necessary and sufficient con...Show More
CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems
2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC)
Year: 2021 | Conference Paper |
Cited by: Papers (8)
Due to the advent of modern embedded systems and mobile devices with constrained resources, there is a great demand for incredibly efficient deep neural networks for machine learning purposes. There is also a growing concern of privacy and confidentiality of user data within the general public when their data is processed and stored in an external server which has further fueled the need for devel...Show More
A Selective Multi-Unit Group Filter-Based Flexible Fast Light-CNN Training
Chan Yung Kim;EunChong Lee;Yumi Kim;Aeri Kim;Sung-Joon Jang;Sang-Seol Lee
2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)
Year: 2023 | Conference Paper |
Grouped convolution is a method extensively used in the design of Convolutional Neural Network (CNN) architecture. Its independent divided grouped filter facilitates the learning and provide possibility of learning various type of features. This reduces the number of parameters and computation costs, making it particularly useful for design lightweight CNN models, which is applicated for mobile de...Show More
Exploring Highly Efficient Compact Neural Networks For Image Classification
2020 IEEE International Conference on Image Processing (ICIP)
Year: 2020 | Conference Paper |
Cited by: Papers (6)
Group convolution works well with many lightweight convolutional neural networks (CNNs) that can effectively reduce the number of parameters and computational cost. However, feature maps of different groups cannot communicate, which restricts their representation capability. To address this issue, in this work, we propose a novel convolution operation named Hierarchical Group Convolution (HGC) for...Show More
Interactive Three-dimension Group Convolution Network with Non-local Fusion Attention for Hyperspectral Image Classifcation
2024 IEEE International Conference on Signal, Information and Data Processing (ICSIDP)
Year: 2024 | Conference Paper |
Three-dimensional convolutional networks (3DC-NNs) have proven to be powerful tools for hyperspectral image (HSI) classification. However, most existing 3DCNN networks optimize global spectral bands, neglecting the distinct reflective characteristics exhibited in different spectral ranges. To address this limitation, we propose a novel Interactive 3D Group Convolution Network (IGCNet) that incorpo...Show More
QGD-Net: A Lightweight Model Utilizing Pixels of Affinity in Feature Layer for Dermoscopic Lesion Segmentation
Jingchao Wang;Guoheng Huang;Guo Zhong;Xiaochen Yuan;Chi-Man Pun;Jie Deng
Response: Pixels with location affinity, which can be also called “pixels of affinity,” have similar semantic information. Group convolution and dilated convolution can utilize them to improve the capability of the model. However, for group convolution, it does not utilize pixels of affinity between layers. For dilated convolution, after multiple convolutions with the same dilated rate, the pixels...Show More
Harmonic analysis of binary functions
2015 IEEE Information Theory Workshop (ITW)
Year: 2015 | Conference Paper |
In this paper we introduce the two-modular Fourier transform of a binary function f : R → R defined over a finite commutative ring R = F2[X]/ϕ(X), where F2[X] is the ring of polynomials with binary coefficients and ϕ(X) is a polynomial of degree n, which is not a multiple of X. We also introduce the corresponding inverse Fourier transform. We then prove the corresponding convolution theorem.Show More
Generalwise Separable Convolution for Mobile Vision Applications
2022 IEEE Symposium Series on Computational Intelligence (SSCI)
Year: 2022 | Conference Paper |
It is acknowledged that the depthwise separable convolution effectively reduces the computational complexity of a standard convolution. However, its depthwise convolution only performs on the spatial domain while neglecting to consider other domains such as the one formed by the channel and width/height dimensions. This paper specifically bridges the gaps by proposing the generalwise separable con...Show More
SdcNet: A Computation-Efficient CNN for Object Recognition
2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)
Year: 2018 | Conference Paper |
Cited by: Papers (3)
Extracting features from a huge amount of data for object recognition is a challenging task. Convolution neural network can be used to meet the challenge, but it often requires a large amount of computation resources. In this paper, a computation-efficient convolutional module, named SdcBlock, is proposed and based on it, the convolution network SdcNet is introduced for object recognition tasks. I...Show More
SRGC-Nets: Sparse Repeated Group Convolutional Neural Networks
Group convolution is widely used in many mobile networks to remove the filter's redundancy from the channel extent. In order to further reduce the redundancy of group convolution, this article proposes a novel repeated group convolutional (RGC) kernel, which has M primary groups, and each primary group includes N tiny groups. In every primary group, the same convolutional kernel is repeated in all...Show More
Research on Classification of Cement-based Electron Microscope Images Based on Improved Residual Network
Wei Liu;Xuguang Wu;Yingbin Wang;Zhiwei Ye;Pan Li;Orest Kochan
2022 IEEE 16th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET)
Year: 2022 | Conference Paper |
Cited by: Papers (2)
In order to automatically identify and classify the cement electron microscope images accurately and quickly, this paper proposes that the residual network ResNet50 is used as the main frame, and the depth separable convolution and grouping convolution are introduced into the residual structure, which reduces the network parameters and computation, accelerates the model convergence and improves th...Show More
ASC Model Based on Feature Stratification and Multichannel ECAP A- TDNN
2022 International Symposium on Advances in Informatics, Electronics and Education (ISAIEE)
Year: 2022 | Conference Paper |
Cited by: Papers (1)
The input audio signal in the acoustic scene classification(ASC) task is composed of multiple acoustic events superimposed on each other, leading to problems such as low recognition rate of complex environments and easy overfitting of the model easily. An ASC model based on feature stratification and multichannel ECAPA- TDNN is proposed to address the above problems. Firstly, the extended harmonic...Show More
A 1.23μJ/Inference, All-Digital Shuffle-Type Group-CNN Accelerator in 28nm CMOS With 85.8% Accuracy on CIFAR-10
To achieve high energy efficiency for edge processing, we implement an all-digital shuffle-type group CNN accelerator with binary weights, which is the first reported shuffle-type GCNN accelerator in CMOS as far as we know. Cross-level optimizations from architecture to hardware level are proposed. The NN architecture is optimized to obtain a hardware-friendly configuration. For hardware-level opt...Show More
Improved Feature Point and Descriptor Extraction Network for SuperPoint
2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)
Year: 2022 | Conference Paper |
Image feature point and descriptor extraction is the basis of SLAM, SFM and 3D reconstruction tasks. In this paper, we study the SuperPoint network, which has good robustness in extracting feature points and descriptors, and introduces the idea of group convolution, replaces the normal convolution with group convolution, and introduces the Mish activation function to replace the ReLU activation fu...Show More
Light Weight Stereo Matching via Deep Extraction and Integration of Low and High Level Information
Xianzhe Xu;Yonghong Hou;Pichao Wang;Zhongyu Jiang;Wanqing Li
2019 IEEE International Conference on Multimedia and Expo (ICME)
Year: 2019 | Conference Paper |
Cited by: Papers (1)
Deep convolutional neural networks (CNN) have demonstrated remarkable progress in stereo matching recently. However, disparity estimation in the ill-posed regions is still difficult. In addition, CNN based stereo matching methods often have impractical computational complexity and memory consumption. To address these problems we propose an end-to-end light weight CNN architecture to effectively le...Show More
A Deep Neural CNN Model with CRF For Breast Mass Segmentation in Mammograms
2021 29th European Signal Processing Conference (EUSIPCO)
Year: 2021 | Conference Paper |
Cited by: Papers (1)
Malignancy in women's breast is known to be the second most common form of cancer. Early detection can help diagnose the disease effectively, but it continues to grow manifolds due to reasons unknown. Therefore, to aid radiologists in the effective treatment of breast cancer, an end-to-end deep learning-based architecture for ROI-based breast mass segmentation is proposed. The architecture involvi...Show More
IEEE Account
Purchase Details
Profile Information
Need Help?
- US & Canada: +1 800 678 4333
- Worldwide: +1 732 981 0060
- Contact & Support
- About IEEE Xplore
- Contact Us
- Help
- Accessibility
- Terms of Use
- Nondiscrimination Policy
- Sitemap
- Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.