OpenGAN: Open-Set Recognition via Open Data Generation
By Shu Kong, Deva Ramanan. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
297 citations recorded by the source corpus.
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 unstable 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.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/815fa9febd615530abccc2430ee05804427394ba
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Andrew Zisserman
- Andrea Vedaldi
- Kai Han
- Sagar Vaze
- Trevor Darrell
- Luc Van Gool
- Joon Son Chung
- Jitendra Malik
Citations in the corpus
- Generalized Category Discovery (2022, background): “GANs are often employed to generate adversarial samples to train an open-set classifier, e.g, [14, 25, 32].”