Towards Efficient Convolutional Network Models with Filter Distribution Templates

17 Apr 2021  ·  Ramon Izquierdo-Cordova, Walterio Mayol-Cuevas ·

Increasing number of filters in deeper layers when feature maps are decreased is a widely adopted pattern in convolutional network design. It can be found in classical CNN architectures and in automatic discovered models. Even CNS methods commonly explore a selection of multipliers derived from this pyramidal pattern. We defy this practice by introducing a small set of templates consisting of easy to implement, intuitive and aggressive variations of the original pyramidal distribution of filters in VGG and ResNet architectures. Experiments on CIFAR, CINIC10 and TinyImagenet datasets show that models produced by our templates, are more efficient in terms of fewer parameters and memory needs.

PDF Abstract
No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.