Striving for Simplicity: The All Convolutional Net — mentioned by dontreact

Wed, 28 Dec 2016 22:16:44 GMT

AllConv networks perform better and are an even simpler modification of the typical CNN architecture: just replace max pool layers with strides convolution. Why did the authors not benchmark against state of the art (also see fractional max pooling) https://arxiv.org/abs/1412.6806

Paper and discussion history. A mention is not an endorsement.

Striving for Simplicity: The All Convolutional Net — mentioned by clickok

Thu, 28 Apr 2016 08:37:37 GMT

The paper itself: http://hi.cs.waseda.ac.jp/~esimo/publications/SimoSerraSIGGR... Part of what makes this neat is that their architecture includes exclusively convolutional layers. Networks that just use such layers have some incredibly useful emergent properties[1] and are about as good as networks with more varied layers[2]. Here they use that to allow for a wide variety of input sizes, because without a fully-connected layer, there's no need to resize images as part of the preprocessing, or indeed at any point inside the network. I am a bit skeptical about it being able to handle "any"…

Paper and discussion history. A mention is not an endorsement.

Striving for Simplicity: The All Convolutional Net · HackerPapers discussions

Striving for Simplicity: The All Convolutional Net — mentioned by dontreact

Striving for Simplicity: The All Convolutional Net — mentioned by clickok