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

Jump to navigation Jump to search
Line 95: Line 95:
|-
|-
| Data augmentation with generative adversarial network (GAN)
| 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.  
| Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this topic, you will learn to use GAN 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.  
| Familiar with machine learning and deep learning; image processing with using python;
| Familiar with machine learning and deep learning; image processing with using python;
| [Yachao Shao, yachao.shao@cs.uni-goettingen.de]
| [Yachao Shao, yachao.shao@cs.uni-goettingen.de]
Retrieved from "https://wiki.net.informatik.uni-goettingen.de/wiki/Seminar_on_Internet_Technologies_(Winter_2020_2021)"