A Novel Weight-Shared Multi-Stage CNN for Scale Robustness

Abstract

Convolutional neural networks (CNNs) have demonstrated remarkable results in image classification for benchmark tasks and practical applications. The CNNs with deeper architectures have achieved even higher performance recently thanks to their robustness to the parallel shift of objects in images as well as their numerous parameters and the resulting high expression ability. However, CNNs have a limited robustness to other geometric transformations such as scaling and rotation. This limits the performance improvement of the deep CNNs, but there is no established solution. This study focuses on scale transformation and proposes a network architecture called the weight-shared multi-stage network (WSMS-Net), which consists of multiple stages of CNNs. The proposed WSMS-Net is easily combined with existing deep CNNs such as ResNet and DenseNet and enables them to acquire robustness to object scaling. Experimental results on the CIFAR-10, CIFAR-100, and ImageNet datasets demonstrate that existing deep CNNs combined with the proposed WSMS-Net achieve higher accuracies for image classification tasks with only a minor increase in the number of parameters and computation time.

accepted version, 13 pages

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Learning in Neural Networks: An Overview
• Striving for Simplicity: The All Convolutional Net
• FitNets: Hints for Thin Deep Nets
• DRAW: A Recurrent Neural Network For Image Generation
• Resnet in Resnet: Generalizing Residual Architectures
• Residual Networks Behave Like Ensembles of Relatively Shallow Networks
• Deep Networks with Stochastic Depth

Cited by in corpus (2)

• Designing and Training of A Dual CNN for Image Denoising
• Virtual neural networks: hundreds of souls in a body