Výsledky vyhledávání - "pointwise convolution"

A two stage deep supervised learning model with inter-layer weight sharing for multi class medical image classification

Autoři: Poonam Moral Debjani Mustafi Sudip Kumar Sahana

Zdroj: Discover Computing, Vol 28, Iss 1, Pp 1-28 (2025)

Témata: Cervical cancer, Convolutional neural network, Pap-Smear images, Inception model, Pointwise convolution, Depthwise convolution, Electronic computers. Computer science, QA75.5-76.95

Popis souboru: electronic resource

Relation: https://doaj.org/toc/2948-2992

Přístupová URL adresa: https://doaj.org/article/a793c55b5f174a0fab9178642fd769b9

Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs

Autoři: Mohammad Qararyah, Fareed Azhar, Muhammad Waqar Maleki, Mohammad Ali a další

Zdroj: Very Efficient Deep Learning in IOT (VEDLIoT) EPI SGA2 53rd International Conference on Parallel Processing, ICPP 2024, Gotland, Sweden ACM International Conference Proceeding Series. :58-67

Témata: layer fusion, depthwise convolution, CNN, vision transformer, pointwise convolution, GPU

Popis souboru: electronic

Přístupová URL adresa: https://research.chalmers.se/publication/542723
https://research.chalmers.se/publication/543131
https://research.chalmers.se/publication/543131/file/543131_Fulltext.pdf

A Hybrid Transformer-LSTM Model With 3D Separable Convolution for Video Prediction

Autoři: Mareeta Mathai Ying Liu Nam Ling

Zdroj: IEEE Access, Vol 12, Pp 39589-39602 (2024)

Témata: self-attention, 3D separable convolution, 0209 industrial biotechnology, 0202 electrical engineering, electronic engineering, information engineering, deep learning, depthwise convolution, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, LSTM, pointwise convolution, TK1-9971

Přístupová URL adresa: https://doaj.org/article/5b081dbb36034408bb4582646b8367f2

Optimized pointwise convolution operation by Ghost blocks

Autoři: Xinzheng Xu Yanyan Ding Zhenhu Lv a další

Zdroj: Electronic Research Archive, Vol 31, Iss 6, Pp 3187-3199 (2023)

Témata: T57-57.97, Applied mathematics. Quantitative methods, QA1-939, mobilenet, ghost-pe, ghost blocks, ghost-pc, pointwise convolution, Mathematics

Přístupová URL adresa: https://doaj.org/article/c38b6fc97eaf4a08a6db2bf87490bd12

A New Pointwise Convolution in Deep Neural Networks Through Extremely Fast and Non Parametric Transforms

Autoři: Joonhyun Jeong Incheon Cho Eunseop Shin a další

Zdroj: IEEE Access, Vol 10, Pp 88251-88262 (2022)

Témata: discrete Walsh-Hadamard transform, Efficient deep neural network architecture, Electrical engineering. Electronics. Nuclear engineering, discrete cosine transform, pointwise convolution, TK1-9971

Přístupová URL adresa: https://doaj.org/article/97ba8a0e0d034adab9aaf2723da06925

Plant Disease Identification Using a Novel Convolutional Neural Network

Autoři: Sk Mahmudul Hassan Arnab Kumar Maji

Zdroj: IEEE Access, Vol 10, Pp 5390-5401 (2022)

Témata: machine learning, 0202 electrical engineering, electronic engineering, information engineering, deep learning, 0401 agriculture, forestry, and fisheries, depthwise convolution, Electrical engineering. Electronics. Nuclear engineering, 04 agricultural and veterinary sciences, 02 engineering and technology, Plant disease, pointwise convolution, TK1-9971

Přístupová URL adresa: https://ieeexplore.ieee.org/ielx7/6287639/9668973/09674894.pdf
https://doaj.org/article/ef5f5ff9416b43ae89d05b79d5fb5407

Index tracking using shapley additive explanations and one-dimensional pointwise convolutional autoencoders

Autoři: Zhang, Yanyi De Smedt, Johannes

Zdroj: ISSN:1057-5219 ; ISSN:1873-8079 ; International Review Of Financial Analysis, vol. 95, Art.No. ARTN 103487.

Témata: Social Sciences, Business, Finance, Business & Economics, Index tracking, Deep learning, Convolutional autoencoder, Pointwise convolution, Feature importance ranking, TIME-SERIES, RETURNS, 1501 Accounting, Auditing and Accountability, 1502 Banking, Finance and Investment, 1801 Law, 3501 Accounting, 3502 Banking, 3801 Applied economics

Popis souboru: application/pdf

Relation: https://lirias.kuleuven.be/handle/20.500.12942/750278; https://doi.org/10.1016/j.irfa.2024.103487

Dostupnost: https://lirias.kuleuven.be/handle/20.500.12942/750278
https://hdl.handle.net/20.500.12942/750278
https://lirias.kuleuven.be/retrieve/24eaaa83-9e2c-4644-9066-23a48271ac33
https://doi.org/10.1016/j.irfa.2024.103487

A Fast Lightweight 3D Separable Convolutional Neural Network With Multi-Input Multi-Output for Moving Object Detection

Autoři: Bingxin Hou Ying Liu Nam Ling a další

Zdroj: IEEE Access, Vol 9, Pp 148433-148448 (2021)

Témata: scene independent evaluation, multi-input multi-output, 0202 electrical engineering, electronic engineering, information engineering, Convolutional neural network, moving object detection, depthwise convolution, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, pointwise convolution, TK1-9971

Přístupová URL adresa: https://ieeexplore.ieee.org/ielx7/6287639/6514899/09592757.pdf
https://doaj.org/article/95b6bf8fc40a4a729d71a7693329d1e2
https://dblp.uni-trier.de/db/journals/access/access9.html#HouLLLR21

Activation Function and Compression Model for Lightweight Convolutional Network

Autoři: XU Zengmin, CHEN Kai, GUO Weiwei, ZHAO Ruwen, JIANG Zhansi

Zdroj: Jisuanji gongcheng, Vol 48, Iss 5, Pp 242-250 (2022)

Témata: transformation of manifold of interest, depthwise seperable convolution, pointwise convolution, self-gating function, kotlin coroutine, Computer engineering. Computer hardware, TK7885-7895, Computer software, QA76.75-76.765

Popis souboru: electronic resource

Relation: https://www.ecice06.com/fileup/1000-3428/PDF/20220532.pdf; https://doaj.org/toc/1000-3428

Přístupová URL adresa: https://doaj.org/article/bc56027d68514095a64e888f5b673d5a

New approaches for the integration of the discrete cosine transform in neural networks for fine-grained image classification

Autoři: Tan, Kelvin Sim Zhen

Témata: convolutional neural network (CNN), fine-grained visual classification (FGVC), discrete cosine transform (DCT), compressed domain image classification, pointwise convolution

Popis souboru: application/pdf

Relation: https://eprints.nottingham.ac.uk/80089/1/18023285-KelvinTanSimZhen_FinalPhdThesis_CORRECTION-2.pdf; Tan, Kelvin Sim Zhen (2025) New approaches for the integration of the discrete cosine transform in neural networks for fine-grained image classification. PhD thesis, University of Nottingham.

Dostupnost: https://eprints.nottingham.ac.uk/80089/

Real-World Railway Traffic Detection Based on Faster Better Network

Autoři: Juan Li Fuqiang Zhou Tao Ye

Zdroj: IEEE Access, Vol 6, Pp 68730-68739 (2018)

Témata: depthwise-pointwise convolution, 0202 electrical engineering, electronic engineering, information engineering, feature fusion, Railway traffic detection, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, efficiency and effectiveness, priori module, TK1-9971

Přístupová URL adresa: https://doaj.org/article/67f4206cdf7b402786de89f17c40847a
https://dblp.uni-trier.de/db/journals/access/access6.html#LiZY18a
https://ieeexplore.ieee.org/document/8528448/

LightLog: A lightweight temporal convolutional network for log anomaly detection on the edge

Autoři: Zumin Wang Jiyu Tian Hui Fang a další

Témata: log anomaly detection, temporal convolutional network, global average pooling, pointwise-convolution, edge computing

Relation: 2134/16961203.v1; https://figshare.com/articles/journal_contribution/LightLog_A_lightweight_temporal_convolutional_network_for_log_anomaly_detection_on_the_edge/16961203

Dostupnost: https://figshare.com/articles/journal_contribution/LightLog_A_lightweight_temporal_convolutional_network_for_log_anomaly_detection_on_the_edge/16961203

Soil-MobiNet: A Convolutional Neural Network Model Base Soil Classification to Determine Soil Morphology and Its Geospatial Location

Autoři: Emmanuel Kwabena Gyasi Swarnalatha Purushotham

Zdroj: Sensors (Basel)
Sensors, Vol 23, Iss 15, p 6709 (2023)
Sensors; Volume 23; Issue 15; Pages: 6709

Témata: 2. Zero hunger, Munsell color chart, precision agriculture, urvara and usara, smartphone, sensors, soil morphology, depthwise pointwise convolution, VITSoil dataset, artificial intelligence, geospatial location, Chemical technology, TP1-1185, 15. Life on land, 6. Clean water, Article

Popis souboru: application/pdf

Přístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/37571493
https://doaj.org/article/ccbf79e753ca495e9602ea2bad334ddf

CPWC:Contextual Point Wise Convolution for Object Recognition

Autoři: Mazumder, Pratik Singh, Pravendra Namboodiri, Vinay

Zdroj: Mazumder, P, Singh, P & Namboodiri, V 2020, CPWC : Contextual Point Wise Convolution for Object Recognition. in 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings., 9054205, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2020-May, IEEE, pp. 4152-4156, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9054205

Témata: convolutional neural network, deep learning, object recognition, Pointwise convolution, /dk/atira/pure/subjectarea/asjc/1700/1712, name=Software, /dk/atira/pure/subjectarea/asjc/1700/1711, name=Signal Processing, /dk/atira/pure/subjectarea/asjc/2200/2208, name=Electrical and Electronic Engineering

Popis souboru: application/pdf

Relation: info:eu-repo/semantics/altIdentifier/isbn/9781509066315; urn:ISBN:9781509066315

Dostupnost: https://researchportal.bath.ac.uk/en/publications/59ab8ace-eae8-4038-8982-dcfd6d5e3be4
https://doi.org/10.1109/ICASSP40776.2020.9054205
https://purehost.bath.ac.uk/ws/files/215043362/ICASSP20_CPWC_Contextual_Point_Wise_Convolution_for_Object_Recognition.pdf
https://www.scopus.com/pages/publications/85089237978

Automatic Railway Traffic Object Detection System Using Feature Fusion Refine Neural Network under Shunting Mode

Autoři: Tao Ye Baocheng Wang Ping Song a další

Zdroj: Sensors, Vol 18, Iss 6, p 1916 (2018)

Témata: shunting mode, feature fusion refine neural network, depthwise-pointwise convolution, effectiveness and real time, Chemical technology, TP1-1185

Relation: http://www.mdpi.com/1424-8220/18/6/1916; https://doaj.org/toc/1424-8220; https://doaj.org/article/245b837753574f7aa7d8fba9f445de7c

Dostupnost: https://doi.org/10.3390/s18061916
https://doaj.org/article/245b837753574f7aa7d8fba9f445de7c

An Enhanced Scheme for Reducing the Complexity of Pointwise Convolutions in CNNs for Image Classification Based on Interleaved Grouped Filters without Divisibility Constraints

Autoři: Joao Paulo Schwarz Schuler Santiago Romani Also Domenec Puig a další

Zdroj: Entropy (Basel)
Entropy, Vol 24, Iss 9, p 1264 (2022)
Entropy; Volume 24; Issue 9; Pages: 1264

Témata: Science, Physics, QC1-999, deep learning, convolutional neural network, 02 engineering and technology, Astrophysics, EfficientNet, computer vision, Article, QB460-466, 03 medical and health sciences, 0302 clinical medicine, 0202 electrical engineering, electronic engineering, information engineering, DCNN, image classification, grouped convolution, pointwise convolution, data analysis, network optimization, parameter reduction, parallel branches, channel interleaving

Popis souboru: application/pdf

Přístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/36141151
https://doaj.org/article/12abed4013b04923ae0bb5fc52ac58eb

Depthwise Separable Convolution Neural Network for High-Speed SAR Ship Detection

Autoři: Tianwen Zhang Xiaoling Zhang Jun Shi a další

Zdroj: Remote Sensing, Vol 11, Iss 21, p 2483 (2019)

Témata: synthetic aperture radar (sar), ship detection, high-speed, convolution neural network (cnn), depthwise separable convolution neural network (ds-cnn), depthwise convolution (d-conv2d), pointwise convolution (p-conv2d), Science

Popis souboru: electronic resource

Relation: https://www.mdpi.com/2072-4292/11/21/2483; https://doaj.org/toc/2072-4292

Přístupová URL adresa: https://doaj.org/article/751b14e9382243978d1fb23bcb66d356

An Enhanced Scheme for Reducing the Complexity of Pointwise Convolutions in CNNs for Image Classification Based on Interleaved Grouped Filters without Divisibility Constraints

Autoři: Universitat Rovira i Virgili Schwarz Schuler, Joao Paulo; Romani Also, Santiago; Puig, Domenec; Rashwan, Hatem; Abdel-Nasser, Mohamed

Zdroj: Entropy; 10.3390/e24091264; Entropy. 24 (9):

Témata: Electrical and Electronic Engineering,Information Systems,Mathematical Physics,Physics and Astronomy (Miscellaneous),Physics, Multidisciplinary, Pointwise convolution, Parameter reduction, Parallel branches, Neural-network, Network optimization, Image classification, Grouped convolution, Efficientnet, Deep learning, Dcnn, Data analysis, Convolutional neural network, Computer vision, Channel interleaving, Saúde coletiva, Physics, multidisciplinary, Physics and astronomy (miscellaneous), Physics and astronomy (all), Medicina ii, Medicina i, Mathematical physics, Matemática / probabilidade e estatística, Interdisciplinar, Information systems, Geociências, General physics and astronomy, Filosofía, Engenharias iv, Engenharias iii, Electrical and electronic engineering, Educação física, Ciências biológicas i, Ciência da computação, Astronomia / física, Journal Publications

URL: http://hdl.handle.net/20.500.11797/imarina9282179

New approaches for the integration of the discrete cosine transform in neural networks for fine-grained image classification

Autoři: Tan, Kelvin Sim Zhen

Témata: convolutional neural network (CNN); fine-grained visual classification (FGVC); discrete cosine transform (DCT); compressed domain image classification; pointwise convolution, Thesis (University of Nottingham only), NonPeerReviewed

URL: https://eprints.nottingham.ac.uk/80089/
https://eprints.nottingham.ac.uk/80089