# OpenGAN

Three experiment setups to validate GAN:
1. open-set discrimination splits a single dataset into open and closed sets. The open-set discrimination classifies open vs closed test examples.
2. open-set recognition requires K-way classification on both closed-set and open-set discrimination.
3. examines the open-set discrimination at pixel level in semantic segmentation, which evaluates pixel-level open-vs-closed classification accuracy.

For (1) and (2), a closed-world K-way network (ResNet18) is trained on the closed training set, whereas in (3), HRNet is used as an OTS network.