Aggregated Residual Transformations for Deep Neural Networks Aggregated Residual Transformations for Deep Neural Networks
Paper summary * Presents an architecture dubbed ResNeXt * They use modules built of * 1x1 conv * 3x3 group conv, keeping the depth constant. It's like a usual conv, but it's not fully connected along the depth axis, but only connected within groups * 1x1 conv * plus a skip connection coming from the module input * Advantages: * Fewer parameters, since the full connections are only within the groups * Allows more feature channels at the cost of more aggressive grouping * Better performance when keeping the number of params constant * Questions/Disadvantages: * Instead of keeping the num of params constant, how about aiming at constant memory consumption? Having more feature channels requires more RAM, even if the connections are sparser and hence there are fewer params * Not so much improvement over ResNet
arxiv.org
arxiv-sanity.com
scholar.google.com
Aggregated Residual Transformations for Deep Neural Networks
Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He
arXiv e-Print archive - 2016 via Local arXiv
Keywords: cs.CV

more

Summary by isarandi 6 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and