Cargando…
Efficient-CapsNet: capsule network with self-attention routing
Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient and for large datasets implies a massive redundancy of feature...
Autores principales: | Mazzia, Vittorio, Salvetti, Francesco, Chiaberge, Marcello |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8290018/ https://www.ncbi.nlm.nih.gov/pubmed/34282164 http://dx.doi.org/10.1038/s41598-021-93977-0 |
Ejemplares similares
-
DA-CapsNet: dual attention mechanism capsule network
por: Huang, Wenkai, et al.
Publicado: (2020) -
CapsNet-SSP: multilane capsule network for predicting human saliva-secretory proteins
por: Du, Wei, et al.
Publicado: (2020) -
RAt-CapsNet: A Deep Learning Network Utilizing Attention and Regional Information for Abnormality Detection in Wireless Capsule Endoscopy
Publicado: (2022) -
Conv-CapsNet: capsule based network for COVID-19 detection through X-Ray scans
por: Sharma, Pulkit, et al.
Publicado: (2023) -
CapsNet-MHC predicts peptide-MHC class I binding based on capsule neural networks
por: Kalemati, Mahmood, et al.
Publicado: (2023)