Seminar on Internet Technologies (Winter 2020 2021): Difference between revisions

Jump to navigation Jump to search
Line 92: Line 92:
| [Weijun Wang, weijun.wang@informatik.uni-goettingen.de]
| [Weijun Wang, weijun.wang@informatik.uni-goettingen.de]
| [https://www.microsoft.com/en-us/research/wp-content/uploads/2017/08/Bahl-MobiCom-2015.pdf]
| [https://www.microsoft.com/en-us/research/wp-content/uploads/2017/08/Bahl-MobiCom-2015.pdf]
| Yes
|-
| Data augmentation with generative adversarial network (GAN)
| Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this work we propose balancing GAN (BAGAN) as an augmentation tool to restore balance in imbalanced datasets. This is challenging because the few minority-class images may not be enough to train a GAN. We overcome this issue by including during the adversarial training all available images of majority and minority classes.
| Familiar with machine learning and deep learning; image processing with using python;
| [Yachao Shao, yachao.shao@cs.uni-goettingen.de]
| [https://arxiv.org/abs/1803.09655]
| Yes
| Yes
|-
|-

Navigation menu