Training Generative Adversarial Networks With Weights
| Autor: | Yannis Pantazis, Yannis Stylianou, Dipjyoti Paul, Michail Fasoulakis |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science business.industry Machine Learning (stat.ML) 020206 networking & telecommunications 02 engineering and technology Variation (game tree) Machine learning computer.software_genre Machine Learning (cs.LG) Image (mathematics) Adversarial system Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Baseline (configuration management) business computer Generative grammar Generator (mathematics) |
| Zdroj: | 2019 27th European Signal Processing Conference (EUSIPCO) EUSIPCO |
| Popis: | The impressive success of Generative Adversarial Networks (GANs) is often overshadowed by the difficulties in their training. Despite the continuous efforts and improvements, there are still open issues regarding their convergence properties. In this paper, we propose a simple training variation where suitable weights are defined and assist the training of the Generator. We provide theoretical arguments why the proposed algorithm is better than the baseline training in the sense of speeding up the training process and of creating a stronger Generator. Performance results showed that the new algorithm is more accurate in both synthetic and image datasets resulting in improvements ranging between 5% and 50%. 6 pages, 3 figures, submitted to Icassp2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|