论文信息 - Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits. The dataset is freely available at this https URL

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

[2] Li Fei-Fei,et al. ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[3] Alex Krizhevsky,et al. Learning Multiple Layers of Features from Tiny Images , 2009 .

[4] Jürgen Schmidhuber,et al. Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5] Yann LeCun,et al. Regularization of Neural Networks using DropConnect , 2013, ICML.

[6] Gregory Cohen,et al. EMNIST: an extension of MNIST to handwritten letters , 2017, CVPR 2017.