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

  1. reconstruction loss 很有用,reconstruction loss可以看作一个regularizer(SWWAE文中提到).
  2. 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

  1. 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

  1. Zhao, J., Mathieu, M., Goroshin, R., and Lecun, Y. Stacked what-where auto-encoders. ArXiv:1506.02351, 2015.
  2. Simonyan, K. and Zisserman, A. Very deep convolutional networks for large-scale image recognition. In ICLR,2015.
  3. 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.
  4. Adaptive deconvolutional networks for mid and high level feature learning
  5. Zeiler, M. D., Krishnan, D., Taylor, G. W., and Fergus, R. Deconvolutional networks. CVPR, 2010.
  6. 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

  1. 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
  2. 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

  1. 【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 ...

  2. 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 ...

  3. [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 ...

  4. [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 ...

  5. [Converge] Training Neural Networks

    CS231n Winter 2016: Lecture 5: Neural Networks Part 2 CS231n Winter 2016: Lecture 6: Neural Networks ...

  6. An Intuitive Explanation of Convolutional Neural Networks

    https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/ An Intuitive Explanation of Convolu ...

  7. 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 ...

  8. 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 ...

  9. 《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

  1. linux多线程学习笔记五--线程安全【转】

    转自:http://blog.csdn.net/kkxgx/article/details/7506085 版权声明:本文为博主原创文章,未经博主允许不得转载. 一,线程安全基础 一个函数被称为线程安 ...

  2. python-rtslib 模块

    Python library for configuring the Linux kernel-based multiprotocol SCSI target (LIO) A Python objec ...

  3. LeetCode OJ-- Edit Distance **

    https://oj.leetcode.com/problems/edit-distance/ 动态规划,它的小规模问题是:当 word1  word2都比较小的时候,word1变成 word2需要的 ...

  4. 点击事件与UICollectionView的代理事件的冲突问题

    发现的问题:在UIImageView上添加UICollectionView视图,点击UICollectionViewCell,不执行didSelectItemAtIndexPath的代理方法. 解决方 ...

  5. (19)python scrapy框架

    安装scrapy pycharm 建个纯python工程 settings里 环境变量设置 C:\Python27;C:\Python27\Scripts; 下载win32api https://so ...

  6. Mycat 做简单的读写分离(转载)

    大漠小狼的个人空间   http://www.51testing.com/html/34/369434-3686088.html 使用Mycat 做简单的读写分离(一) 原本使用的是amoeba做的读 ...

  7. linux svn co 重新迁出

    在linux环境下,使用svn co (即svn checkout) 报svn: Authorization failed错误, 使用svn co svn://localhost/temp.cc /d ...

  8. java.sql.Timestamp类型

    如果想向数据库中插入日期时间的话,可以用java.sql.Timestamp类 一个与 java.util.Date类有关的瘦包装器 (thin wrapper),它允许 JDBC API 将该类标识 ...

  9. wpa破解学习

    TENDA  159031106A iPhone 192.168.0.11 90:27:E4:53:49:D6 18:58:52 PC-201211262044 192.168.0.12 00:F1: ...

  10. python模块相关

    aniso8601 pyquery networkx (2.0)                 - Python package for creating and manipulating grap ...