33
/fr/
AIzaSyB4mHJ5NPEv-XzF7P6NDYXjlkCWaeKw5bc
November 1, 2025
3939981
363911
2
Public Timelines
FAQ Obtenir le Premium

7 nov 2014 - Speeding up convolutional neural networks with low rank expansions. (BMVC 2014)

Description:

Two-component Decomposition

This is achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain.


结果:
在场景文本字符识别设计的真实世界网络中,在准确率没有损失的情况下,可能获得2.5倍的加速比,在准确率下降不到1%的情况下,可能达到4.5倍的加速比,在标准基准测试中仍然达到了最先进的水平。

Ajouté au bande de temps:

7 avr. 2020
0
0
283

Date:

7 nov 2014
Maintenaint
~ Il y a 10 ans