Multi-Scale CapsNet: A Novel Traffic Sign Recognition Method

Abstract

Convolutional Neural Networks (CNNs) have performed very well on image classification tasks, but CNNs is insensitive to detailed image information and requires a large amount of training data and time. Capsule Networks(CapsNets) can solve this problem very well, but the Baseline CapsNet model is very shallow, and the extraction of low-level features is not enough. We propose a Multi-Scale Capsule Network (Multi-Scale CapsNet), by extracting the low-level features of images with multi-channel convolution of multiple convolution kernels, so extracted features are more diverse, then passing from the bottom layer to the upper layer in the form of a "capsule", which encapsulats the multidimensional features of the image in the form of a vector, thus the features are saved in the network, rather than being recovered after being lost. In the German Traffic Sign Recognition Benchmark(GTSRB), we obtained competitive results with the accuracy of 99.4%, which is better than the human performance of 98.81% and the Multi-Scale Convolutional Neural Network(MS-CNN) of 97.33%.

A lightweight network for traffic sign recognition based on multi-scale feature and attention mechanism

“…Using a weighted mixed loss function may require manual selection of weights, which may result in poor model performance if the weights are not selected well. Chen proposed a Multi-Scale Capsule Network (Multi-Scale CapsNet) [ 25 ]. Image features are extracted by multi-channel convolution of multi-convolution kernel, which makes the extracted features more diversified.…”