Filter Distribution Templates in Convolutional Networks for Image Classification Tasks
This work addresses efficiency and performance improvements for neural network design in image classification, though it appears incremental as it builds on existing architectures.
The paper tackles the problem of optimizing filter distribution in convolutional neural networks for image classification, finding that modifying filter patterns can improve accuracy by up to 8.9% while reducing parameters by up to 54%.
Neural network designers have reached progressive accuracy by increasing models depth, introducing new layer types and discovering new combinations of layers. A common element in many architectures is the distribution of the number of filters in each layer. Neural network models keep a pattern design of increasing filters in deeper layers such as those in LeNet, VGG, ResNet, MobileNet and even in automatic discovered architectures such as NASNet. It remains unknown if this pyramidal distribution of filters is the best for different tasks and constrains. In this work we present a series of modifications in the distribution of filters in four popular neural network models and their effects in accuracy and resource consumption. Results show that by applying this approach, some models improve up to 8.9% in accuracy showing reductions in parameters up to 54%.