CNN网络结构 - Refining Architectures of Deep Convolutional Neural Networks

78 篇文章 0 订阅
36 篇文章 0 订阅

CVPR 2016
Refining Architectures of Deep Convolutional Neural Networks

本文的出发点是回答下面的问题: is the selected CNN optimal for the dataset in terms of accuracy and model size?
针对一个现有的多类别数据集,使用CNN进行分类,那么我们选择的CNN 模型在精度和模型大小上是否是最优的?

Given a pre-trained CNN for a specific dataset, refine the architecture in order to potentially increase the accuracy while possibly reducing the model size

这里我们定义了两个操作方法来调整模型使其最优。

这里写图片描述

Intuition behind our approach: 给定一个数据集,固定网络的深度,怎么最好的区分数据集上的类别?我们的方法首先从一个预训练好的CNN模型开始,然后学习该数据集中所有类在每一个卷积层上的区分度。基于数据集的属性,数据集中某一些类在较低的卷积层区分度较好,另一些类在较低的卷积层区分度则较低。类似的波动在较高的卷积层也可以被发现。和给定层的前一层相比较,该给定层对某些类可以增加区分,对另些类可以降低区分。区分度增加的类的数目和增加该层的神经元个数有关( stretching / widening);区分度降低的类的数目和对称切分该层的神经元有关( symmetric splitting)。所以 stretch and split操作可以同时应用于每一卷积层。stretch 或 split 的多少不仅取决于对当前层类别区分能力的影响,还取决于对其后续层的类别区分度影响。当 stretch and split 的操作固定下来后,我们可以调整网络,在相同的数据集上重新训练。

结果对比:
这里写图片描述

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 2
    评论
Deep Convolutional Neural Networks (CNNs) are a special type of Neural Networks, which have shown state-of-the-art results on various competitive benchmarks. The powerful learning ability of deep CNN is largely achieved with the use of multiple feature extraction stages that can automatically learn hierarchical representations from the data. Availability of a large amount of data and improvements in the hardware processing units have accelerated the research in CNNs, and recently very interesting deep CNN architectures are reported. The recent race in developing deep CNN architectures has shown that the innovative architectural ideas, as well as parameter optimization, can improve the CNN performance on various vision-related tasks. In this regard, different ideas in the CNN design have been explored such as the use of different activation and loss functions, parameter optimization, regularization, and restructuring of the processing units. However, the major improvement in representational capacity of the deep CNN is achieved by the restructuring of the processing units. Especially, the idea of using a block as a structural unit instead of a layer is receiving substantial attention. This survey thus focuses on the intrinsic taxonomy present in the recently reported deep CNN architectures and consequently, classifies the recent innovations in CNN architectures into seven different categories. These seven categories are based on spatial exploitation, depth, multi-path, width, feature map exploitation, channel boosting, and attention. Additionally, it covers the elementary understanding of the CNN components and sheds light on the current challenges and applications of CNNs.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值