University of Michigan - Ann Arbor

Xie et al.  proposed a variant of ResNet that is codenamed ResNeXt with the following building block:
This may look familiar to you as it is very similar to the Inception module of  GoogleNet, they both follow the split-transform-merge paradigm, except in this variant, the outputs of different paths are merged by adding them together, while in  GoogleNet they are depth-concatenated. Another difference is that in  GoogleNet, each path is different (1x1, 3x3 and 5x5 convolution) from each other, while in this architecture, all paths share the same topology.

Learn Before

Related