Results 51 to 60 of about 73,468 (309)

Clifford-steerable convolutional neural networks [PDF]

We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of E(p,q)-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces Rp,q.
Weiler, M., Forré, P.D., Lucic, A.; id_orcid, Zhdanov, M., Ruhe, D., Brandstetter, J., Forré, P.   +6 more
core   +8 more sources

Convolutional Neural Networks in the Inspection of Serrasalmids (Characiformes) Fingerlings

Animals
Aquaculture produces more than 122 million tons of fish globally. Among the several economically important species are the Serrasalmidae, which are valued for their nutritional and sensory characteristics.
Marília Parreira Fernandes, Adriano Carvalho Costa, Heyde Francielle do Carmo França, Alene Santos Souza, Pedro Henrique de Oliveira Viadanna, Lessandro do Carmo Lima, Liege Dauny Horn, Matheus Barp Pierozan, Isabel Rodrigues de Rezende, Rafaella Machado dos S. de Medeiros, Bruno Moraes Braganholo, Lucas Oliveira Pereira da Silva, Jean Marc Nacife, Kátia Aparecida de Pinho Costa, Marco Antônio Pereira da Silva, Rodrigo Fortunato de Oliveira   +15 more
doaj   +1 more source

A systematic study of the class imbalance problem in convolutional neural networks [PDF]

, 2018
In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue.
Buda, Mateusz,, Mazurowski, Maciej A.,, Maki, Atsuto,   +2 more
core   +1 more source

CEModule: A Computation Efficient Module for Lightweight Convolutional Neural Networks [PDF]

, 2021
Lightweight convolutional neural networks (CNNs) rely heavily on the design of lightweight convolutional modules (LCMs). For an LCM, lightweight design based on repetitive feature maps (LoR) is currently one of the most effective approaches.
Liang, Y, Li, M, Liu, G, Jiang, C
core   +1 more source

Humans can decipher adversarial images

Nature Communications, 2019
Convolutional Neural Networks (CNNs) have reached human-level benchmarks in classifying images, but they can be “fooled” by adversarial examples that elicit bizarre misclassifications from machines.
Zhenglong Zhou, Chaz Firestone
doaj   +1 more source

Two-Branch Convolutional Neural Network with Polarized Full Attention for Hyperspectral Image Classification

Remote Sensing, 2023
In recent years, convolutional neural networks (CNNs) have been introduced for pixel-wise hyperspectral image (HSI) classification tasks. However, some problems of the CNNs are still insufficiently addressed, such as the receptive field problem, small ...
Haimiao Ge, Liguo Wang, Moqi Liu, Yuexia Zhu, Xiaoyu Zhao, Haizhu Pan, Yanzhong Liu   +6 more
doaj   +1 more source

A Practical Noise2Noise Denoising Pipeline for High‐Throughput Raman Spectroscopy

Advanced Engineering Materials, EarlyView.
A lightweight and reproducible denoising pipeline for high‐throughput Raman spectroscopy is introduced, based on a 1D convolutional autoencoder trained with a Noise2Noise strategy. Using only repeated short‐exposure acquisitions, the method suppresses stochastic noise without reference spectra, enabling reliable spectral reconstruction while preserving
David Martin‐Calle, Cesar Alvarez‐Llamas, Vincent Motto‐Ros, Christophe Dujardin, Jérémie Margueritat, David Rodney   +5 more
wiley   +1 more source

Learning shape correspondence with anisotropic convolutional neural networks [PDF]

, 2016
Convolutional neural networks have achieved extraordinary results in many computer vision and pattern recognition applications; however, their adoption in the computer graphics and geometry processing communities is limited due to the non-Euclidean ...
Rodolà, Emanuele, Bronstein, Michael, Masci, Jonathan, Boscaini, Davide, Bronstein, Michael M.   +4 more
core  

A novel online ensemble convolutional neural networks for streaming data [PDF]

, 2019
In this study, we introduce an online ensemble method based on convolutional neural networks (CNNs) for streaming data. Recent work has shown that a convolution operation has been an effective way to extract features.
Pham, XC, Liew, AWC, Nguyen, TTT
core   +1 more source

Convolutional neural networks for decoding electroencephalography responses and visualizing trial by trial changes in discriminant features. [PDF]

, 2021
BACKGROUND Deep learning has revolutionized the field of computer vision, where convolutional neural networks (CNNs) extract complex patterns of information from large datasets.
Göktepe, Pinar, Aellen, Florence Marcelle, Apostolopoulos, Stefanos, Tzovara, Athina   +3 more
core   +1 more source