Abstract
Recently, Convolutional Neural Networks (CNN) has been used in variety of domains, including fashion classification. Social media, e-commerce, and criminal law are extensively applicable in this field. CNNs are efficient to train and found to give the most accurate results in solving real world problems. In this paper, we use Fashion MNIST dataset for evaluating the performance of convolutional neural network based deep learning architectures. We compare most common deep learning architectures such as AlexNet, GoogleNet, VGG, ResNet, DenseNet and SqueezeNet to find the best performance. We additionally propose a simple modification to the architecture to improve and accelerate learning process. We report accuracy measurements (93.43%) and the value of loss function (0.19) using our proposed method and show its significant improvements over other architectures.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Meshkini, K.H., Ghassemian, H.: Texture classification using shearlet transform and GLCM. In: Iranian International Conference of Electrical Engineering (2017)
Bhatnagar, S.H., Ghosal, D., Kolekar, M.H.: Classification of fashion article images using convolutional neural networks. In: Fourth International Conference on Image Information Processing (ICIIP) (2017)
Lin, K., et al.: Deep learning-based segmentation and quantification of cucumber powdery mildew using convolutional neural network. Frontiers Plant Sci. (2019)
LeCun, Y., et al.: Gradient-based learning applied to document recognition. In: Processing of the IEEE (1998)
Madhavi, K.V., Tamikodi, R., Sudha, K.J.: An innovative method for retrieving relevant images by getting the top-ranked images first using interactive genetic algorithm. In: 7th International Conference on Communication, Computing and Virtualization (2016)
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747
Yamashita, R., et al.: Convolutional neural networks: an overview and application in radiology. Insights Imaging 9(4), 611–629 (2018)
Zhao, Z.-Q., et al.: Object detection with deep learning: a review. J. Latex Class Files 14(8) (2017)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. J. Neural Comput. 18, 1527–1554 (2006)
Rowley, H.A., Baluja, S.H., Kanade, T.: Neural network-based face detection. Comput. Vis. Pattern Recogn. (1996)
Sermanet, P., et al.: Pedestrian detection with unsupervised multi-stage feature learning. arXiv preprint arXiv:1212.0142
Ferreira, B.Q., Faria, J., Baia, L., Sousa, R.G.: A unified model with structured output for fashion images classification. arXiv preprint arXiv:1806.09445v1
Sharma, N., Jain, V., Mishra, A.: An analysis of convolutional neural networks for image classification. In: International Conference on Computational Intelligence and Data Science (ICCIDS) (2018)
Agarap, A.M.: An architecture combining convolutional neural network (CNN) and support vector machine (SVM) for image classification. arXiv preprint arXiv:1712.03541v1
Bhandre, A., et al.: Applications of convolutional neural networks. Int. J. Comput. Sci. Inf. Technol. 7(5), 2206–2215 (2016)
Shamsuddin, M.R., et al.: Exploratory analysis of MNIST handwritten digit for machine learning modelling. In: International Conference on Soft Computing in Data Science (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60 (2017)
Szegedy, C.H., et al.: Going deeper with convolutions. arXiv preprint arXiv:1409.4842
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
He, K., Zhang, X., Ren, S.H., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385
Huang, G., Liu, Z.H., Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. arXiv preprint arXiv:1608.06993v5
Iandola, F.N., et al.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360v4
Han, S., et al.: Regularizing deep neural networks with dense-sparse-dense training flow. arXiv:1607.04381 (2016)
Kingma, D.P., Lei Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980v9
Bjorck, J., et al.: Understanding batch normalization. arXiv preprint arXiv:1806.02375v4
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Meshkini, K., Platos, J., Ghassemain, H. (2020). An Analysis of Convolutional Neural Network for Fashion Images Classification (Fashion-MNIST). In: Kovalev, S., Tarassov, V., Snasel, V., Sukhanov, A. (eds) Proceedings of the Fourth International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’19). IITI 2019. Advances in Intelligent Systems and Computing, vol 1156. Springer, Cham. https://doi.org/10.1007/978-3-030-50097-9_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-50097-9_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50096-2
Online ISBN: 978-3-030-50097-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)