Guiding InfoGAN with Semi-supervision
| Autor: | Otmar Hilliges, Adrian Spurr, Emre Aksan |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
business.industry
Computer science media_common.quotation_subject 02 engineering and technology Latent variable Mutual information 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences ComputingMethodologies_PATTERNRECOGNITION Convergence (routing) 0202 electrical engineering electronic engineering information engineering Code (cryptography) 020201 artificial intelligence & image processing Quality (business) Artificial intelligence Architecture business computer Categorical variable Generative grammar 0105 earth and related environmental sciences media_common |
| Zdroj: | Machine Learning and Knowledge Discovery in Databases ISBN: 9783319712482 ECML/PKDD (1) Proceedings of Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2017 Lecture Notes in Computer Science Lecture Notes in Computer Science-Machine Learning and Knowledge Discovery in Databases |
| ISSN: | 0302-9743 1611-3349 |
| Popis: | In this paper we propose a new semi-supervised GAN architecture (ss-InfoGAN) for image synthesis that leverages information from few labels (as little as \(0.22\%\), max. \(10\%\) of the dataset) to learn semantically meaningful and controllable data representations where latent variables correspond to label categories. The architecture builds on Information Maximizing Generative Adversarial Networks (InfoGAN) and is shown to learn both continuous and categorical codes and achieves higher quality of synthetic samples compared to fully unsupervised settings. Furthermore, we show that using small amounts of labeled data speeds-up training convergence. The architecture maintains the ability to disentangle latent variables for which no labels are available. Finally, we contribute an information-theoretic reasoning on how introducing semi-supervision increases mutual information between synthetic and real data. Code related to this chapter is available at: https://github.com/spurra/ss-infogan. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|