Measuring (in)variances in Convolutional Networks

Convolutional neural networks (CNN) offer state-of-the-art performance in various computer vision tasks such as activity recognition, face detection, medical image analysis, among others. Many of those tasks need invariance to image transformations (i.e.. rotations, translations or scaling). This w...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Quiroga, Facundo, Torrents-Barrena, Jordina, Lanzarini, Laura Cristina, Puig, Domenec
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2019
Materias:
Ciencias Informáticas
transformation invariance
rotation invariance
Neural networks
variance measure
MNIST dataset
CIFAR10 dataset
Residual Network
VGG Network
AllConvolutional Network
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/80387
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata

Ejemplares similares

Ejemplares similares