作者利用各种优化方法提取图像的feature map,避免了普通Convolutional Neural Network中得encoder部分。
参考资料:
Deconvolutional Networks, Matthew D. Zeiler, Dilip Krishnan, Graham W. Taylor and Rob Fergus.
【Papers】《Deconvolutional Networks》阅读笔记
原文:http://www.cnblogs.com/sunshineatnoon/p/3959907.html