About Pyramid Structure in Convolutional Neural Networks

2016/08/14 by Ihsan Ullah, Ullah, Ihsan, Alfredo Petrosino +1 · 2 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1608.04064

Published in 2016 International Joint Conference on Neural Networks (IJCNN)

arxiv created 2016/08/14 · arxiv updated 2016/08/16

Abstract

Deep convolutional neural networks (CNN) brought revolution without any doubt to various challenging tasks, mainly in computer vision. However, their model designing still requires attention to reduce number of learnable parameters, with no meaningful reduction in performance. In this paper we investigate to what extend CNN may take advantage of pyramid structure typical of biological neurons. A generalized statement over convolutional layers from input till fully connected layer is introduced that helps further in understanding and designing a successful deep network. It reduces ambiguity, number of parameters, and their size on disk without degrading overall accuracy. Performance are shown on state-of-the-art models for MNIST, Cifar-10, Cifar-100, and ImageNet-12 datasets. Despite more than 80% reduction in parameters for Caffe_LENET, challenging results are obtained. Further, despite 10-20% reduction in training data along with 10-40% reduction in parameters for AlexNet model and its variations, competitive results are achieved when compared to similar well-engineered deeper architectures.

Cited by

• Semi-supervised Deep Transfer for Regression without Domain Alignment
• 3DPyranet Features Fusion for Spatio-temporal Feature Learning

Related

• Convolutional Neural Networks:
• Convolutional Neural Pyramid for Image Processing
• Convolutional Neural Networks Exploiting Attributes of Biological Neurons
• Deep Pyramidal Residual Networks
• Convolutional Neural Networks In Convolution