Multiplicative Noise Channel in Generative Adversarial Networks
| Autor: | Xinhan Di, Pengqian Yu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Channel (digital image)
Computer science business.industry 010501 environmental sciences 01 natural sciences Multiplicative noise 03 medical and health sciences symbols.namesake Noise 0302 clinical medicine Gaussian noise Face (geometry) symbols Artificial intelligence business Algorithm 030217 neurology & neurosurgery MNIST database 0105 earth and related environmental sciences |
| Zdroj: | ICCV Workshops |
| DOI: | 10.1109/iccvw.2017.141 |
| Popis: | Additive Gaussian noise is widely used in generative adversarial networks (GANs). It is shown that the convergence speed is increased through the application of the additive Gaussian noise. However, the performance such as the visual quality of generated samples and semiclassification accuracy is not improved. This is partially due to the high uncertainty introduced by the additive noise. In this paper, we introduce multiplicative noise which has lower uncertainty under technical conditions, and it improves the performance of GANs. To demonstrate its practical use, two experiments including unsupervised human face generation and semi-classification tasks are conducted. The results show that it improves the state-of-art semi-classification accuracy on three benchmarks including CIFAR-10, SVHN and MNIST, as well as the visual quality and variety of generated samples on GANs with the additive Gaussian noise. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|