Very Deep convolutional Networks for large-scale Image Recognitionkaren Simonyan, Andrew Zisserman
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image Recogni tion setting. Our main contribution are a thorough evaluation of networks of increasing depth, which shows that a significant improvement On the Prior-art configurations can is achieved by pushing the depth to 16–19 weight layers. These findings were the basis of our ImageNet challenge, where our team submission the first and the secured P Laces in the localisation and classification tracks respectively.
Look at the summary, almost know what the author is going to explain, depth!!!!!!
Google's model is also depth ah, so Shuicheng Yan slides said their model is not the deep enough!
Very Deep convolutional Networks for large-scale Image recognition