【文献阅读】Augmenting Supervised Neural Networks with Unsupervised Objectives-ICML-2016
一、Abstract
从近期对unsupervised learning 的研究得到启发,在large-scale setting 上,本文把unsupervised learning 与supervised learning结合起来,提高了supervised learning的性能。主要是把autoencoder与CNN结合起来
二、Key words:
SAE;SWWAE; reconstruction;encoder;decoder;VGG-16;Alex-Net
三、 Motivation
- reconstruction loss 很有用,reconstruction loss可以看作一个regularizer(SWWAE文中提到).
- unsupervised learning会对model起一定的限定作用,即相当于一个regularizer,这个regularizer使得encoder阶段提取得到的特征具有可解释性
四、Main contributions
- 本文实验表明了,high-capacity neural networks(采用了known switches)的 intermediate activations 可以保存input的大量信息,除了部分
2.通过结合decoder pathway 的loss,提升了supervised learning model的分类正确率
3.做了几个 autoencoder模型的对比实验,发现: the pooling switches and the layer-wise reconstruction loss 非常重要!
五、Inspired by
- Zhao, J., Mathieu, M., Goroshin, R., and Lecun, Y. Stacked what-where auto-encoders. ArXiv:1506.02351, 2015.
- Simonyan, K. and Zisserman, A. Very deep convolutional networks for large-scale image recognition. In ICLR,2015.
- Krizhevsky, A., Sutskever, I., and Hinton, G. E. Imagenet classification with deep convolutional neural networks.In NIPS, 2012.
Rasmus, A., Valpola, H., Honkala, M., Berglund, M., and Raiko, T. Semi-supervised learning with ladder network.In NIPS, 2015. - Adaptive deconvolutional networks for mid and high level feature learning
- Zeiler, M. D., Krishnan, D., Taylor, G. W., and Fergus, R. Deconvolutional networks. CVPR, 2010.
- Zeiler, M., Taylor, G., and Fergus, R. Adaptive deconvolu-tional networks for mid and high level feature learning.In ICCV, 2011.
key word:SWWAE;VGG-16;Alex-Net;ladder-Net;Deconvolutional network
六、文献具体实验及结果
1.SAE-all模型的训练:
第一步,采用VGG-16(训练好的VGG-16)初始化encoder,采用gaussian初始化decoder
第二步,固定encoder部分,用layerwise的方法训练decoder
第三步,用数据整体的训练更新decoder和encoder的参数
SAE-first模型的训练同SAE-all
SAE-layerwise一般只是拿来初始化 SAE-first SAE-all
SWWAE-all 提升了 1.66 % and 1.18% for single-crop and convolution schemes.
(top-1)
七、 感悟
- 2006~2010年期间, unsupervised learning 盛行是以为当时有标签数据不够大,所以需要用unsupervised leanring 的方法来初始化网络,可以取得较好效果,而 类似imagenet这样的大量标签数据的出现, 用autoencoder来初始化网络的优势已经没有。从这里也可以知道,当数据量较小时,可以考虑用unsupervised learning 的方法来初始化网络,从而提升分类准确率
- reconstruction loss 可以看作 regularization , 即是对enconder的weights做了一些限制,限制其获得的activations要能recon出input,是的提取得到的特征具有可解释性
【文献阅读】Augmenting Supervised Neural Networks with Unsupervised Objectives-ICML-2016的更多相关文章
- 【文献阅读】Self-Normalizing Neural Networks
Self-Normalizing Neural Networks ,长达93页的附录足以成为吸睛的地方(给人感觉很厉害), 此paper提出了新的激活函数,称之为 SELUs ,其具有normaliz ...
- 论文阅读 Streaming Graph Neural Networks
3 Streaming Graph Neural Networks link:https://dl.acm.org/doi/10.1145/3397271.3401092 Abstract 本文提出了 ...
- [ufldl]Supervised Neural Networks
要实现的部分为:forward prop, softmax函数的cost function,每一层的gradient,以及penalty cost和gradient. forwad prop forw ...
- [C3] Andrew Ng - Neural Networks and Deep Learning
About this Course If you want to break into cutting-edge AI, this course will help you do so. Deep l ...
- [Converge] Training Neural Networks
CS231n Winter 2016: Lecture 5: Neural Networks Part 2 CS231n Winter 2016: Lecture 6: Neural Networks ...
- An Intuitive Explanation of Convolutional Neural Networks
https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/ An Intuitive Explanation of Convolu ...
- 论文笔记之:Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
Learning Multi-Domain Convolutional Neural Networks for Visual Tracking CVPR 2016 本文提出了一种新的CNN 框架来处理 ...
- How to Use Convolutional Neural Networks for Time Series Classification
How to Use Convolutional Neural Networks for Time Series Classification 2019-10-08 12:09:35 This blo ...
- 《Graph Neural Networks: A Review of Methods and Applications》阅读笔记
本文是对文献 <Graph Neural Networks: A Review of Methods and Applications> 的内容总结,详细内容请参照原文. 引言 大量的学习 ...
随机推荐
- soap1.1与soap1.2区别
- error: expected class-name before '{' token(转)
错误原因 1. 头文件引用的类中,结尾可能少了; ,, 例如:class Cwj{} 忘记了以;结尾哦. 2. 引用的头文件的顺序先后相互冲突:例如:Msg类中包含了#includ ...
- this关键字、this()、super()
对于下面的代码怎么区分是哪个对象调用当前方法: Class Banana { void peel(int i); } publci Class BananaPeel { public static v ...
- CodeForces 702B Powers of Two【二分/lower_bound找多少个数/给出一个数组 求出ai + aj等于2的幂的数对个数】
B. Powers of Two You are given n integers a1, a2, ..., an. Find the number of pairs of indexes i, ...
- codevs——2102 石子归并 2(区间DP)
时间限制: 10 s 空间限制: 256000 KB 题目等级 : 黄金 Gold 题解 查看运行结果 题目描述 Description 在一个园形操场的四周摆放N堆石子,现要将石子有次序地 ...
- 维生素d
作者:卓正内科李爽 链接:https://www.guokr.com/article/440438/来源:果壳本文版权属于果壳网(guokr.com),禁止转载.如有需要,请联系sns@guokr.c ...
- 2016北京集训测试赛(十三) Problem B: 网络战争
Solution KD tree + 最小割树
- Android为什么方法数不能超过65535
言归正传,来聊聊为什么方法数不能超过65535?搬上Dalvik工程师在SF上的回答,因为在Dalvik指令集里,调用方法的invoke-kind指令中,method reference index只 ...
- MFC中 自定义消息
想在对话框显示出来后立即执行一段代码. 方法之一是自定义消息,即添加一个自定义的消息在消息队列中等待对话框初始化之后从消息队列中读取消息执行代码. 在OnInitDialog返回之前post一个自定义 ...
- C++/C# 托管扩展 更改概要 [转]
源文 :https://msdn.microsoft.com/zh-cn/library/ms235298%28v=vs.100%29.aspx Visual Studio 2010 其他版本 此概要 ...