Search Results for author:
Found 2 papers, 0 papers with code
RaViTT: Random Vision Transformer Tokens
Results show that RaViTT increases the accuracy of the baseline in all datasets and outperforms the SOTA augmentation techniques in 3 out of 4 datasets by a significant margin +1. 23% to +4. 32%.
Uncovering Bias in Face Generation Models
The contribution of this work is a novel analysis covering architectures and embedding spaces for fine-grained understanding of bias over three approaches: generators, attribute modifier, and post-processing bias mitigators.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
