33
/
AIzaSyAYiBZKx7MnpbEhh9jyipgxe19OcubqV5w
August 1, 2025
3273489
291599
1
Public Timelines
Public TimelinesFAQ
Public TimelinesFAQ
For educational institutions For teachers For students Cabinet
For educational institutions For teachers For students Open cabinet
Create
Create a timeline
Public timelines
Library
FAQ

aug 23, 2019 - Zi Wang: Towards Efficient Convolutional Neural Networks Through Low-Error Filter Saliency Estimation, PRICAI, 2019

Description:

基于滤波显著性的信道修剪是一种最先进的深卷积神经网络压缩和加速方法。本文提出了一个系统的通道修剪方法，显著降低了滤波器显著性的估计误差。与现有的方法不同，我们的方法在预训练过程中引入了交替方向乘法器（ADMM），大大降低了网络中参数的大小.

Added to timeline:

Pruning

By龚成
30 Aug 2019
1
0
612

Date:

aug 23, 2019
Now
~ 5 years and 9 months ago
About & FeedbackTermsPrivacyLibraryFAQ
Support 24/7  
CabinetGet premium
Donate
The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.
Secured with SSL