Towards Efficient Convolutional Network Models with Filter Distribution Templates
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 AbstractTasks
Datasets
CIFAR-10
CIFAR-100
Tiny ImageNet
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.
