Classification of fashion article images using convolutional neural networks

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.

[1]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[2]  S. Sengupta,et al.  Hidden Markov model based video indexing with discrete cosine transform as a likelihood function , 2004, Proceedings of the IEEE INDICON 2004. First India Annual Conference, 2004..

[3]  Emmanuel Dufourq,et al.  EDEN: Evolutionary deep networks for efficient machine learning , 2017, 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech).

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[7]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[8]  Sanjay N. Talbar,et al.  Texture Segmentation using Fractal Signature , 2000 .

[9]  M.H. Kolekar,et al.  Semantic Indexing of News Video Sequences: A Multimodal Hierarchical Approach Based on Hidden Markov Model , 2005, TENCON 2005 - 2005 IEEE Region 10 Conference.

[10]  Leon A. Gatys,et al.  A Neural Algorithm of Artistic Style , 2015, ArXiv.

[11]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[12]  Maheshkumar H. Kolekar,et al.  Bayesian belief network based broadcast sports video indexing , 2011, Multimedia Tools and Applications.

[13]  Pushpak Bhattacharyya,et al.  IITP at SemEval-2017 Task 5: An Ensemble of Deep Learning and Feature Based Models for Financial Sentiment Analysis , 2017, *SEMEVAL.

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Guna Seetharaman,et al.  Semantic Concept Mining Based on Hierarchical Event Detection for Soccer Video Indexing , 2009, J. Multim..

[16]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[18]  Somnath Sengupta,et al.  Hidden Markov Model Based Structuring of Cricket Video Sequences Using Motion and Color Features , 2004, ICVGIP.

[19]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[20]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[21]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[22]  Somnath Sengupta,et al.  Bayesian Network-Based Customized Highlight Generation for Broadcast Soccer Videos , 2015, IEEE Transactions on Broadcasting.