一种用于数据高效深度学习的空间可变视觉通路模型。
A Space-Variant Visual Pathway Model for Data Efficient Deep Learning.
作者信息
Ozimek Piotr, Hristozova Nina, Balog Lorinc, Siebert Jan Paul
机构信息
Computer Vision for Autonomous Systems Group, School of Computing Science, University of Glasgow, Glasgow, United Kingdom.
出版信息
Front Cell Neurosci. 2019 Mar 26;13:36. doi: 10.3389/fncel.2019.00036. eCollection 2019.
We present an investigation into adopting a model of the retino-cortical mapping, found in biological visual systems, to improve the efficiency of image analysis using Deep Convolutional Neural Nets (DCNNs) in the context of robot vision and egocentric perception systems. This work has now enabled DCNNs to process input images approaching in size, , using only consumer grade graphics processor (GPU) hardware .
我们展示了一项关于采用生物视觉系统中发现的视网膜-皮质映射模型的研究，目的是在机器人视觉和自我中心感知系统的背景下，利用深度卷积神经网络（DCNN）提高图像分析的效率。这项工作现已使DCNN能够仅使用消费级图形处理器（GPU）硬件来处理尺寸接近 的输入图像。
Zotero 插件