OpenGAN: Open-Set Recognition via Open Data Generation

Shu Kong     Deva Ramanan

[lng_lat_ecef]       [lng_lat_ecef]



[lng_lat_ecef]


Abstract. Real-world machine learning systems need to analyze test data that may differ from training data. In K-way classification, this is crisply formulated as open-set recognition, core to which is the ability to discriminate open-set data outside the K closed-set classes. Two conceptually elegant ideas for open-set discrimination are: 1) discriminatively learning an open-vs-closed binary discriminator by exploiting some outlier data as the open-set, and 2) unsupervised learning the closed-set data distribution with a GAN, using its discriminator as the open-set likelihood function. However, the former generalizes poorly to diverse open test data due to overfitting to the training outliers, which are unlikely to exhaustively span the open-world. The latter does not work well, presumably due to the instable training of GANs. Motivated by the above, we propose OpenGAN, which addresses the limitation of each approach by combining them with several technical insights. First, we show that a carefully selected GAN-discriminator on some real outlier data already achieves the state-of-the-art. Second, we augment the available set of real open training examples with adversarially synthesized ``fake'' data. Third and most importantly, we build the discriminator over the features computed by the closed-world K-way networks. This allows OpenGAN to be implemented via a lightweight discriminator head built on top of an existing K-way network. Extensive experiments show that OpenGAN significantly outperforms prior open-set methods.

12min Talk



keywords. Open-Set Recognition, Open-World, Generative Adversarial Networks, Semantic Segmentation


Paper


Citing this work

If you find this work useful in your research, please consider citing:

@inproceedings{OpenGAN,
           title={OpenGAN: Open-Set Recognition via Open Data Generation},
           author={Kong, Shu and Ramanan, Deva},
           booktitle={ICCV},
           year={2021}
           }
      
@article{OpenGAN_PAMI,
            title={OpenGAN: Open-Set Recognition via Open Data Generation},
            author={Kong, Shu and Ramanan, Deva},
            journal={IEEE PAMI},
            year={2022}
            }

Acknowledgement

This work was supported by the CMU Argo AI Center for Autonomous Vehicle Research

Useful Links

Open-set recognition deals with unknown examples encountered in the real open world. If you are interested in solving issues related to the open-world, you might find the workshops below interesting.