Approach

The realization of Inception models has been accompanied with a series of complicating factors — the filter numbers and sizes are tailored for each individual transformation, and the modules are customized stage-by-stage. Although careful combinations of these components yield excellent neural network recipes, it is in general unclear how to adapt the Inception architectures to new datasets/tasks, especially when there are many factors and hyper-parameters to be designed.

In this paper, we present a simple architecture which adopts VGG/ResNets’ strategy of repeating layers, while exploiting the split-transform-merge strategy in an easy, extensible way.

Equivalent buildingblocks of ResNeXt

Experiment