Skip to Content

441 Results Found

  • Article
  • Open Access
1,174 Views
21 Pages

To address the limitations of insufficient feature representation, large model size, and high deployment cost in network traffic classification, a lightweight classification framework based on multi-teacher knowledge distillation is proposed. The fra...

  • Article
  • Open Access
38 Citations
5,992 Views
19 Pages

2 February 2021

Automatic Modulation Classification (AMC) is of paramount importance in wireless communication systems. Existing methods usually adopt a single category of neural network or stack different categories of networks in series, and rarely extract differe...

(This article belongs to the Section Electrical, Electronics and Communications Engineering)
  • Article
  • Open Access
8 Citations
3,701 Views
18 Pages

The primary objective of person re-identification is to identify individuals from surveillance videos across various scenarios. Conventional pedestrian recognition models typically employ convolutional neural network (CNN) and vision transformer (ViT...

(This article belongs to the Topic Computer Vision and Image Processing, 2nd Edition)
  • Article
  • Open Access
67 Citations
5,412 Views
20 Pages

11 March 2023

The segmentation algorithm for buildings and waters is extremely important for the efficient planning and utilization of land resources. The temporal and space range of remote sensing pictures is growing. Due to the generic convolutional neural netwo...

(This article belongs to the Special Issue Application of Artificial Intelligence in Land Use and Land Cover Mapping II)
  • Article
  • Open Access
17 Citations
2,815 Views
24 Pages

Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical Sensing

  • Yajie He,
  • Ningyi Zhang,
  • Xinjin Ge,
  • Siqi Li and ,
  • Linfeng Yang,
  • Minghao Kong,
  • Yiping Guo and
  • Chunli Lv
  • + 3 authors+ 0 author

A disease detection network based on a sparse parallel attention mechanism is proposed and experimentally validated in the passion fruit (Passiflora edulis [Sims]) disease detection task. Passiflora edulis, as a tropical and subtropical fruit tree, i...

(This article belongs to the Special Issue How Optical Sensors and Deep Learning Enhance the Production Management in Smart Agriculture)
  • Article
  • Open Access
4 Citations
6,977 Views
28 Pages

Efficient Convolutional Neural Networks Utilizing Fine-Grained Fast Fourier Transforms

  • Yulin Zhang,
  • Feipeng Li,
  • Haoke Xu,
  • Xiaoming Li and
  • Shan Jiang

22 September 2024

Convolutional Neural Networks (CNNs) are among the most prevalent deep learning techniques employed across various domains. The computational complexity of CNNs is largely attributed to the convolution operations. These operations are computationally...

(This article belongs to the Topic Advances in Integrative AI, Machine Learning, and Big Data for Transformative Applications)
  • Article
  • Open Access
7 Citations
4,092 Views
19 Pages

Using CNN with Multi-Level Information Fusion for Image Denoising

  • Shaodong Xie,
  • Jiagang Song,
  • Yuxuan Hu,
  • Chengyuan Zhang and
  • Shichao Zhang

Deep convolutional neural networks (CNN) with hierarchical architectures have obtained good results for image denoising. However, in some cases where the noise level is unknown and the image background is complex, it is challenging to obtain robust i...

(This article belongs to the Special Issue Big Model Techniques for Image Processing)
  • Article
  • Open Access
9 Citations
4,605 Views
21 Pages

FPGA Acceleration of CNNs-Based Malware Traffic Classification

  • Lin Zhang,
  • Bing Li,
  • Yong Liu,
  • Xia Zhao and ,
  • Yazhou Wang and
  • Jiaxin Wu
  • + 1 author+ 0 author

With the rapid development of the Internet, malware traffic is seriously endangering the security of cyberspace. Convolutional neural networks (CNNs)-based malware traffic classification can automatically learn features from raw traffic, avoiding the...

(This article belongs to the Special Issue Application of Electronic Devices on Intelligent System)
  • Article
  • Open Access
4 Citations
3,339 Views
17 Pages

3 November 2022

Optical music recognition (OMR) refers to converting musical scores into digitized information using electronics. In recent years, few types of OMR research have involved numbered musical notation (NMN). The existing NMN recognition algorithm is diff...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
30 Citations
7,307 Views
19 Pages

Context Aggregation Network for Semantic Labeling in Aerial Images

  • Wensheng Cheng,
  • Wen Yang,
  • Min Wang,
  • Gang Wang and
  • Jinyong Chen

15 May 2019

Semantic labeling for high resolution aerial images is a fundamental and necessary task in remote sensing image analysis. It is widely used in land-use surveys, change detection, and environmental protection. Recent researches reveal the superiority...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
4 Citations
3,349 Views
18 Pages

6 September 2024

Edge detection is a crucial issue in computer vision, with convolutional neural networks (CNNs) being a key component in various systems for detecting edges within images, offering numerous practical implementations. This paper introduces a hybrid ap...

  • Article
  • Open Access
4 Citations
1,205 Views
23 Pages

Oat Ears Detection and Counting Model in Natural Environment Based on Improved Faster R-CNN

  • Cong Tian,
  • Jiawei Wang,
  • Decong Zheng,
  • Yangen Li and
  • Xinchi Zhang

23 February 2025

In order to enable oat ears to be quickly and accurately identified in the natural environment, this paper proposes an oat ears detection and counting model based on an improved Faster R-CNN. In the backbone network, the commonly used single convolut...

(This article belongs to the Section Precision and Digital Agriculture)
  • Article
  • Open Access
65 Citations
6,824 Views
16 Pages

Coarse-Fine Convolutional Deep-Learning Strategy for Human Activity Recognition

  • Carlos Avilés-Cruz,
  • Andrés Ferreyra-Ramírez,
  • Arturo Zúñiga-López and
  • Juan Villegas-Cortéz

31 March 2019

In the last decade, deep learning techniques have further improved human activity recognition (HAR) performance on several benchmark datasets. This paper presents a novel framework to classify and analyze human activities. A new convolutional neural...

(This article belongs to the Section Physical Sensors)
  • Article
  • Open Access
14 Citations
2,443 Views
23 Pages

In hyperspectral image (HSI) classification, each pixel is assigned to a specific land cover type, which is critical for applications in environmental monitoring, agriculture, and urban planning. Convolutional neural network (CNN) and Transformers ha...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
2 Citations
2,798 Views
11 Pages

30 September 2024

With the development of Convolutional Neural Networks (CNNs), there is a growing requirement for their deployment on edge devices. At the same time, Compute-In-Memory (CIM) technology has gained significant attention in edge CNN applications due to i...

(This article belongs to the Section Circuit and Signal Processing)
  • Article
  • Open Access
36 Citations
8,117 Views
22 Pages

A Hardware-Friendly High-Precision CNN Pruning Method and Its FPGA Implementation

  • Xuefu Sui,
  • Qunbo Lv,
  • Liangjie Zhi,
  • Baoyu Zhu and ,
  • Yuanbo Yang,
  • Yu Zhang and
  • Zheng Tan
  • + 2 authors+ 0 author

11 January 2023

To address the problems of large storage requirements, computational pressure, untimely data supply of off-chip memory, and low computational efficiency during hardware deployment due to the large number of convolutional neural network (CNN) paramete...

(This article belongs to the Section Remote Sensors)
  • Article
  • Open Access
43 Citations
6,120 Views
19 Pages

Multipath Residual Network for Spectral-Spatial Hyperspectral Image Classification

  • Zhe Meng,
  • Lingling Li,
  • Xu Tang,
  • Zhixi Feng and ,
  • Licheng Jiao and
  • Miaomiao Liang
  • + 1 author+ 0 author

13 August 2019

Convolutional neural networks (CNNs) have recently shown outstanding capability for hyperspectral image (HSI) classification. In this work, a novel CNN model is proposed, which is wider than other existing deep learning-based HSI classification model...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
69 Citations
14,091 Views
20 Pages

Speech Emotion Recognition Using Convolution Neural Networks and Multi-Head Convolutional Transformer

  • Rizwan Ullah,
  • Muhammad Asif,
  • Wahab Ali Shah,
  • Fakhar Anjam and ,
  • Ibrar Ullah,
  • Tahir Khurshaid,
  • Lunchakorn Wuttisittikulkij,
  • Shashi Shah,
  • Syed Mansoor Ali and
  • Mohammad Alibakhshikenari
  • + 5 authors+ 0 author

7 July 2023

Speech emotion recognition (SER) is a challenging task in human–computer interaction (HCI) systems. One of the key challenges in speech emotion recognition is to extract the emotional features effectively from a speech utterance. Despite the pr...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
5 Citations
2,926 Views
14 Pages

20 March 2025

Surface classification is critical for ground robots operating in diverse environments, as it improves mobility, stability, and adaptability. This study introduces IMU-based deep learning models for surface classification as a low-cost alternative to...

(This article belongs to the Special Issue Recent Developments in Machine Design, Automation and Robotics)
  • Article
  • Open Access
8 Citations
2,322 Views
14 Pages

Human pose estimation is a complex detection task in which the network needs to capture the rich information contained in the images. In this paper, we propose MSTPose (Multi-Scale Transformer for human Pose estimation). Specifically, MSTPose leverag...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
6 Citations
4,358 Views
21 Pages

12 May 2020

This paper proposes a novel three-dimensional direction-of-arrival (3D-DOA) estimation method for electromagnetic (EM) signals using convolutional neural networks (CNN) in a Gaussian or non-Gaussian noise environment. First of all, in the presence of...

(This article belongs to the Special Issue Signal Processing Techniques for Smart Sensor Communications)
  • Article
  • Open Access
1,317 Views
14 Pages

13 August 2025

This study presents a reconfigurable optical convolutional neural network (CNN) architecture that integrates a crossbar switch network into a smart-pixel-based optical CNN (SPOCNN) framework. The SPOCNN leverages smart pixel light modulators (SPLMs),...

(This article belongs to the Section Optoelectronics)
  • Article
  • Open Access
39 Citations
3,905 Views
14 Pages

7 October 2022

Different types of partial discharge (PD) in gas-insulated switchgear (GIS) cause different damage to GIS insulation, correctly identifying the PD type is very important for evaluating the insulation status of GIS. This paper proposes a PD pattern re...

(This article belongs to the Special Issue Application of Artificial Intelligence in Power System Monitoring and Fault Diagnosis)
  • Article
  • Open Access
10 Citations
4,129 Views
18 Pages

8 June 2024

Multi-factor authentication (MFA) is a system for authenticating an individual’s identity using two or more pieces of data (known as factors). The reason for using more than two factors is to further strengthen security through the use of addit...

(This article belongs to the Special Issue Integrating Artificial Intelligence in Renewable Energy Systems)
  • Article
  • Open Access
5 Citations
4,758 Views
18 Pages

A Configurable and Fully Synthesizable RTL-Based Convolutional Neural Network for Biosensor Applications

  • Pervesh Kumar,
  • Huo Yingge,
  • Imran Ali,
  • Young-Gun Pu and ,
  • Keum-Cheol Hwang,
  • Youngoo Yang,
  • Yeon-Jae Jung,
  • Hyung-Ki Huh,
  • Seok-Kee Kim and
  • Kang-Yoon Lee
  • + 6 authors+ 1 author

23 March 2022

This paper presents a register-transistor level (RTL) based convolutional neural network (CNN) for biosensor applications. Biosensor-based diseases detection by DNA identification using biosensors is currently needed. We proposed a synthesizable RTL-...

(This article belongs to the Section Biosensors)
  • Article
  • Open Access
4 Citations
1,763 Views
22 Pages

Multi-Scale Electromechanical Impedance-Based Bolt Loosening Identification Using Attention-Enhanced Parallel CNN

  • Xingyu Fan,
  • Jiaming Kong,
  • Haoyang Wang,
  • Kexin Huang and ,
  • Tong Zhao and
  • Lu Li
  • + 1 author+ 0 author

4 September 2025

Bolted connections are extensively utilized in aerospace, civil, and mechanical systems for structural assembly. However, inevitable structural vibrations can induce bolt loosening, leading to preload reduction and potential structural failure. Early...

  • Article
  • Open Access
3,381 Views
18 Pages

Flexible Convolver for Convolutional Neural Networks Deployment onto Hardware-Oriented Applications

  • Moisés Arredondo-Velázquez,
  • Paulo Aaron Aguirre-Álvarez,
  • Alfredo Padilla-Medina,
  • Alejandro Espinosa-Calderon and ,
  • Juan Prado-Olivarez and
  • Javier Diaz-Carmona
  • + 1 author+ 0 author

21 December 2022

This paper introduces a flexible convolver capable of adapting to the different convolution layer configurations of state-of-the-art Convolution Neural Networks (CNNs). The use of two proposed programmable components achieves this adaptability. A Pro...

(This article belongs to the Section Electrical, Electronics and Communications Engineering)
  • Review
  • Open Access
16 Citations
6,704 Views
59 Pages

18 October 2025

As the complexity of convolutional neural networks (CNN) continues to increase, efficient deployment on computationally constrained hardware platforms has become a significant challenge. Against this backdrop, field-programmable gate arrays (FPGA) em...

  • Article
  • Open Access
52 Citations
9,104 Views
26 Pages

FPGA-Based Vehicle Detection and Tracking Accelerator

  • Jiaqi Zhai,
  • Bin Li,
  • Shunsen Lv and
  • Qinglei Zhou

16 February 2023

A convolutional neural network-based multiobject detection and tracking algorithm can be applied to vehicle detection and traffic flow statistics, thus enabling smart transportation. Aiming at the problems of the high computational complexity of mult...

(This article belongs to the Special Issue Application of Deep Learning in Intelligent Transportation)
  • Article
  • Open Access
3 Citations
1,841 Views
20 Pages

Precipitation Spatio-Temporal Forecasting in China via DC-CNN-BiLSTM

  • Peng Shu,
  • Xiaoqi Duan,
  • Chenming Shao,
  • Jie Liu and ,
  • Youliang Tian and
  • Sheng Li
  • + 1 author+ 0 author

4 May 2025

Accurate and reliable precipitation prediction remains a significant challenge due to an incomplete understanding of regional meteorological dynamics and limitations in forecasting routine weather events. To overcome these challenges, we propose a no...

(This article belongs to the Section Water, Agriculture and Aquaculture)
  • Feature Paper
  • Article
  • Open Access
44 Citations
9,328 Views
19 Pages

Remote Sensing Big Data Classification with High Performance Distributed Deep Learning

  • Rocco Sedona,
  • Gabriele Cavallaro,
  • Jenia Jitsev,
  • Alexandre Strube and ,
  • Morris Riedel and
  • Jón Atli Benediktsson
  • + 1 author+ 0 author

17 December 2019

High-Performance Computing (HPC) has recently been attracting more attention in remote sensing applications due to the challenges posed by the increased amount of open data that are produced daily by Earth Observation (EO) programs. The unique parall...

(This article belongs to the Special Issue Analysis of Big Data in Remote Sensing)
  • Article
  • Open Access
9 Citations
3,931 Views
18 Pages

21 October 2023

Convolutional neural networks (CNNs) are used for classification, as they can extract complex features from input data. The training and inference of these networks typically require platforms with CPUs and GPUs. To execute the forward propagation of...

(This article belongs to the Topic Machine Learning in Internet of Things)
  • Article
  • Open Access
4 Citations
3,072 Views
16 Pages

18 November 2022

In multi-tasking scenarios with dynamically changing loads, the parallel computing of convolutional neural networks (CNNs) causes high energy and resource consumption in the system. Another critical problem is that previous neural network hardware ac...

(This article belongs to the Special Issue Embedded Systems for Neural Network Applications)
  • Article
  • Open Access
14 Citations
3,124 Views
19 Pages

Enhancement of Underwater Images through Parallel Fusion of Transformer and CNN

  • Xiangyong Liu,
  • Zhixin Chen,
  • Zhiqiang Xu,
  • Ziwei Zheng and ,
  • Fengshuang Ma and
  • Yunjie Wang
  • + 1 author+ 0 author

Ocean exploration is crucial for utilizing its extensive resources. Images captured by underwater robots suffer from issues such as color distortion and reduced contrast. To address the issue, an innovative enhancement algorithm is proposed, which in...

(This article belongs to the Section Ocean Engineering)
  • Feature Paper
  • Article
  • Open Access
5 Citations
10,580 Views
14 Pages

Rotation Invariant Networks for Image Classification for HPC and Embedded Systems

  • Rosemberg Rodriguez Salas,
  • Petr Dokladal and
  • Eva Dokladalova

Convolutional Neural Network (CNNs) models’ size reduction has recently gained interest due to several advantages: energy cost reduction, embedded devices, and multi-core interfaces. One possible way to achieve model reduction is the usage of R...

(This article belongs to the Special Issue Energy Aware HPC Revisited: AI Concerns, Architectures and Optimization Strategies)
  • Feature Paper
  • Article
  • Open Access
13 Citations
4,578 Views
16 Pages

Wave-Encoded Model-Based Deep Learning for Highly Accelerated Imaging with Joint Reconstruction

  • Jaejin Cho,
  • Borjan Gagoski,
  • Tae Hyung Kim,
  • Qiyuan Tian and ,
  • Robert Frost,
  • Itthi Chatnuntawech and
  • Berkin Bilgic
  • + 2 authors+ 0 author

A recently introduced model-based deep learning (MoDL) technique successfully incorporates convolutional neural network (CNN)-based regularizers into physics-based parallel imaging reconstruction using a small number of network parameters. Wave-contr...

(This article belongs to the Special Issue AI in MRI: Frontiers and Applications)
  • Article
  • Open Access
15 Citations
3,889 Views
18 Pages

28 September 2022

Automatic detection of arrhythmia using electrocardiogram (ECG) and deep learning (DL) is very important to reduce the global death rate from cardiovascular diseases (CVD). Previous studies on automatic arrhythmia detection relied largely on various...

(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
  • Article
  • Open Access
22 Citations
6,209 Views
20 Pages

Efficient FPGA Implementation of Convolutional Neural Networks and Long Short-Term Memory for Radar Emitter Signal Recognition

  • Bin Wu,
  • Xinyu Wu,
  • Peng Li,
  • Youbing Gao and ,
  • Jiangbo Si and
  • Naofal Al-Dhahir
  • + 1 author+ 0 author

30 January 2024

In recent years, radar emitter signal recognition has enjoyed a wide range of applications in electronic support measure systems and communication security. More and more deep learning algorithms have been used to improve the recognition accuracy of...

(This article belongs to the Special Issue Radar Signal Detection, Recognition and Identification)
  • Article
  • Open Access
21 Citations
6,066 Views
16 Pages

A 3D Fluorescence Classification and Component Prediction Method Based on VGG Convolutional Neural Network and PARAFAC Analysis Method

  • Kun Ruan,
  • Shun Zhao,
  • Xueqin Jiang,
  • Yixuan Li and ,
  • Jianbo Fei,
  • Dinghua Ou,
  • Qiang Tang,
  • Zhiwei Lu,
  • Tao Liu and
  • Jianguo Xia
  • + 5 authors+ 0 author

12 May 2022

Three-dimensional fluorescence is currently studied by methods such as parallel factor analysis (PARAFAC), fluorescence regional integration (FRI), and principal component analysis (PCA). There are also many studies combining convolutional neural net...

(This article belongs to the Section Environmental Sciences)
  • Article
  • Open Access
15 Citations
4,046 Views
26 Pages

11 October 2022

Charts are often used for the graphical representation of tabular data. Due to their vast expansion in various fields, it is necessary to develop computer algorithms that can easily retrieve and process information from chart images in a helpful way....

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
47 Citations
8,484 Views
20 Pages

Urban Land Cover Classification of High-Resolution Aerial Imagery Using a Relation-Enhanced Multiscale Convolutional Network

  • Chun Liu,
  • Doudou Zeng,
  • Hangbin Wu,
  • Yin Wang and ,
  • Shoujun Jia and
  • Liang Xin
  • + 1 author+ 0 author

17 January 2020

Urban land cover classification for high-resolution images is a fundamental yet challenging task in remote sensing image analysis. Recently, deep learning techniques have achieved outstanding performance in high-resolution image classification, espec...

(This article belongs to the Special Issue Lightweight Deep Neural Networks for Remote Sensing Image Understanding)
  • Article
  • Open Access
11 Citations
2,771 Views
13 Pages

Research on Predicting Remain Useful Life of Rolling Bearing Based on Parallel Deep Residual Network

  • Xingang Wang,
  • Dongkai Qiao,
  • Kaizhong Han,
  • Xiaohui Chen and
  • Ziqiu He

24 April 2022

The prediction of bearing remaining useful life (RUL) plays a pivotal role in ensuring the safe operation of machinery and reducing maintenance loss. Traditional prediction methods only consider the features of one domain or integrate the features of...

(This article belongs to the Section Mechanical Engineering)
  • Article
  • Open Access
3 Citations
2,142 Views
12 Pages

Convolutional Neural Networks (CNNs) are fundamental to modern AI applications but often suffer from significant memory bottlenecks due to non-contiguous access patterns during convolution operations. Although previous work has optimized data layouts...

(This article belongs to the Special Issue FPGA-Based Reconfigurable Embedded Systems)
  • Article
  • Open Access
4 Citations
2,712 Views
20 Pages

Novel Tunable Pseudoresistor-Based Chopper-Stabilized Capacitively Coupled Amplifier and Its Machine Learning-Based Application

  • Mohammad Aleem Farshori,
  • M. Nizamuddin,
  • Renuka Chowdary Bheemana,
  • Krishna Prakash and ,
  • Shonak Bansal,
  • Mohammad Zulqarnain,
  • Vipin Sharma,
  • S. Sudhakar Babu and
  • Kanwarpreet Kaur
  • + 4 authors+ 0 author

29 August 2025

This work presents a high-common-mode-rejection-ratio (CMRR) and high-gain FinFET-based bio-potential amplifier with a novel CMRR reduction technique. In this paper, a feedback buffer is used alongside a capacitively coupled chopper-stabilized circui...

  • Article
  • Open Access
1 Citations
1,969 Views
15 Pages

5 October 2025

This paper presents a dual-structured convolutional neural network (CNN) for image classification, which integrates two parallel branches: CNN-A with spatial attention and CNN-B with channel attention. The spatial attention module in CNN-A dynamicall...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
7 Citations
2,052 Views
18 Pages

20 January 2025

As the core component of an airplane, the health status of the aviation engine is crucial for the safe operation of the aircraft. Therefore, predicting the remaining service life of the engine is of great significance for ensuring its safety and reli...

  • Review
  • Open Access
202 Views
30 Pages

Fully homomorphic encryption (FHE) enables a server to evaluate a neural network on encrypted inputs. The Cheon–Kim–Kim–Song (CKKS) scheme supports approximate arithmetic over packed vectors, making it suitable for the linear comput...

(This article belongs to the Section Cryptography Reviews)
  • Article
  • Open Access
1 Citations
2,130 Views
17 Pages

WRA-MF: A Bit-Level Convolutional-Weight-Decomposition Approach to Improve Parallel Computing Efficiency for Winograd-Based CNN Acceleration

  • Siwei Xiang,
  • Xianxian Lv,
  • Yishuo Meng,
  • Jianfei Wang and ,
  • Cimang Lu and
  • Chen Yang
  • + 1 author+ 0 author

8 December 2023

FPGA-based convolutional neural network (CNN) accelerators have been extensively studied recently. To exploit the parallelism of multiplier–accumulator computation in convolution, most FPGA-based CNN accelerators heavily depend on the number of...

(This article belongs to the Special Issue FPGA-Based Deep Neural Network Accelerators Using Emerging Technologies)
  • Article
  • Open Access
3 Citations
3,085 Views
23 Pages

MPFINet: A Multilevel Parallel Feature Injection Network for Panchromatic and Multispectral Image Fusion

  • Yuting Feng,
  • Xin Jin,
  • Qian Jiang,
  • Quanli Wang and ,
  • Lin Liu and
  • Shaowen Yao
  • + 1 author+ 0 author

2 December 2022

The fusion of a high-spatial-resolution panchromatic (PAN) image and a corresponding low-resolution multispectral (MS) image can yield a high-resolution multispectral (HRMS) image, which is also known as pansharpening. Most previous methods based on...

(This article belongs to the Section Earth Observation Data)
  • Article
  • Open Access
2 Citations
4,112 Views
17 Pages

CSGN: Combined Channel- and Spatial-Wise Dynamic Gating Architecture for Convolutional Neural Networks

  • Sangmin Hyun,
  • Chang Ho Ryu,
  • Ju Yeon Kang,
  • Hyun Jo Lim and
  • Tae Hee Han

26 August 2022

The explosive computation and memory requirements of convolutional neural networks (CNNs) hinder their deployment in resource-constrained devices. Because conventional CNNs perform identical parallelized computations even on redundant pixels, the sal...

(This article belongs to the Section Artificial Intelligence)

of 9