BriefGPT.xyz
Dec, 2014
深层轮换散射用于目标分类
Deep Roto-Translation Scattering for Object Classification
HTML
PDF
Edouard Oyallon, Stéphane Mallat
TL;DR
本文介绍一种基于波浪变换滤波器的深度散射卷积网络,通过引入几何先验知识来细化图像特征提取,从而实现图像分类和理解的目标。
Abstract
dictionary learning
algorithms or supervised
deep convolution networks
have considerably improved the efficiency of predefined feature representations such as SIFT. We introduce a deep scattering convolution netw
→