Classification of fashion article images using convolutional neural networks

Abstract

In this paper, we propose a state-of-the-art model for classification of fashion article images. We trained convolutional neural network based deep learning architectures to classify images in the Fashion-MNIST dataset. We have proposed three different convolutional neural network architectures and used batch normalization and residual skip connections for ease and acceleration of learning process. Our model shows impressive results on the benchmark dataset of Fashion-MNIST. Comparisons show that our proposed model reports improved accuracy of around 2% over the existing state-of-the-art systems in literature.