zoukankan      html  css  js  c++  java
  • Diabetic Retinopathy Winner's Interview: 1st place, Ben Graham

    Diabetic Retinopathy Winner's Interview: 1st place, Ben Graham

    Ben Graham finished at the top of the leaderboard in the high-profileDiabetic Retinopathy competition. In this blog, he shares his approach on a high-level with key takeaways. Ben finished 3rd in the National Data Science Bowl, a competition that helped develop many of the approaches used to compete in this challenge.

    Screen Shot 2015-09-10 at 11.33.04 AM

    Ben's Kaggle profile

    The Basics

    What made you decide to enter this competition?

    I wanted to experiment with training CNNs with larger images to see what kind of architectures would work well. Medical images can in some ways be more challenging than classifying regular photos as the important features can be very small.

    Let's Get Technical

    What preprocessing and supervised learning methods did you use?

    For preprocessing, I first scaled the images to a given radius. I then subtracted local average color to reduce differences in lighting.

    Screen Shot 2015-09-10 at 11.12.53 AM

    For supervised learning, I experimented with convolutional neural network architectures. To map the network predictions to the integer labels needed for the competition, I used a random forest so that I could combine the data from the two eyes to make each prediction.

    Screen Shot 2015-09-10 at 11.14.11 AM

    Were you surprised by any of your findings?

    I was surprised by a couple of things. First, that increasing the scale of the images beyond radius=270 pixels did not seem to help. I was expecting the existence of very small features, only visible at higher resolutions, to tip the balance in favor of larger images. Perhaps the increase in processing times for larger images was too great.

    I was also surprised by the fact that ensembling (taking multiple views of each image, and combining the results of different networks) did very little to improve accuracy. This is rather different to the case of normal photographs, where ensembling can make a huge difference.

    Which tools did you use?

    Python and OpenCV for preprocessing. SparseConvNet for processing. I was curious to see if I could sparsify the images during preprocessing; however, due to time constraints I didn't get that working. SparseConvNet implements fractional max-pooling, which allowed me to experiment with different types of spatial data aggregation.

    Bio

    Ben Graham is an Assistant Professor at the University of Warwick, UK. His research interests are probabilistic spatial models such as percolation, and machine learning.

  • 相关阅读:
    asp Excel导入数据库
    Excel导出函数
    asp精简checkbox全选代码
    一个操作读写已存在excel 文件的例子
    asp中实现网络打印功能
    asp操作excel 技术总结
    asp初学者常用的代码
    asp连接各种其他数据库 的方法
    asp得到地址栏里"?"以后的字串
    asp判断今天是星期几
  • 原文地址:https://www.cnblogs.com/yymn/p/4801910.html
Copyright © 2011-2022 走看看