Cargando…
Compact Image-Style Transfer: Channel Pruning on the Single Training of a Network
Recent image-style transfer methods use the structure of a VGG feature network to encode and decode the feature map of the image. Since the network is designed for the general image-classification task, it has a number of channels and, accordingly, requires a huge amount of memory and high computati...
Autores principales: | Kim, Minseong, Choi, Hyun-Chul |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9653671/ https://www.ncbi.nlm.nih.gov/pubmed/36366125 http://dx.doi.org/10.3390/s22218427 |
Ejemplares similares
-
Total Style Transfer with a Single Feed-Forward Network
por: Kim, Minseong, et al.
Publicado: (2022) -
Toward Exploiting Second-Order Feature Statistics for Arbitrary Image Style Transfer
por: Choi, Hyun-Chul
Publicado: (2022) -
Dynamical Conventional Neural Network Channel Pruning by Genetic Wavelet Channel Search for Image Classification
por: Chen, Lin, et al.
Publicado: (2021) -
Lossless Reconstruction of Convolutional Neural Network for Channel-Based Network Pruning
por: Lee, Donghyeon, et al.
Publicado: (2023) -
Cartoon-Style Image Rendering Transfer Based on Neural Networks
por: Wang, Lei
Publicado: (2022)