Unofficial PyTorch Implementation of Robust Classification with Convolutional Prototype Learning
The original paper is available at: https://arxiv.org/abs/1805.03438
The dataset is downloaded from the source (http://www.iro.umontreal.ca/~lisa/deep/data/mnist/mnist.pkl.gz), mentioned in the official Tensorflow repository (https://github.com/YangHM/Convolutional-Prototype-Learning).
- Run main.py to train the model.
- Run extract_features.py to extract the hidden layer features
- Run visualize_scatter.py to generate the scatter plot
Features with DCE loss:
Features with GCPL: