Gopika Sudhakaran

Aug 26, 2024 | arxiv.org | Markus Reuter |Stefan Roth |Gopika Sudhakaran |Dominik Gojny

[Submitted on 26 Aug 2024] Title:DIAGen: Diverse Image Augmentation with Generative Models View a PDF of the paper titled DIAGen: Diverse Image Augmentation with Generative Models, by Tobias Lingenberg and 5 other authors View PDF HTML (experimental) Abstract:Simple data augmentation techniques, such as rotations and flips, are widely used to enhance the generalization power of computer vision models. However, these techniques often fail to modify high-level semantic attributes of a class.