• Hae Beom Lee (KAIST), Juho Lee (Univ. Oxford), Saehoon Kim (AITRICS), Eunho Yang (KAIST), and Sung Ju Hwang (KAIST)

This is the Tensor-Flow implementation for the paper DropMax: Adaptive Variationial Softmax (NeurIPS 2018) : https://arxiv.org/abs/1712.07834

If you found the provided code useful, please cite our work.

@inproceedings{lee2018dropmax,
    author    = {Hae Beom Lee and Juho Lee and Saehoon Kim and Eunho Yang and Sung Ju Hwang},
    title     = {DropMax: Adaptive Variationial Softmax},
    booktitle = {NeurIPS},
    year      = {2018}
}

1. Modify --mnist_path, in run.sh
2. Specify --model among softmax or dropmax, in run.sh
3. Run run.sh

Note that LeNet is used as the base network for this code, whereas in the paper we used the network in the Tensorflow-Tutorial (refer to https://gist.github.com/saitodev/c4c7a8c83f5aa4a00e93084dd3f848c5). But the training results and tendencies are similar.