no code implementations • 19 Jun 2023 • Felipe A. Quezada, Carlos F. Navarro, Cristian Muñoz, Manuel Zamorano, Jorge Jara-Wilde, Violeta Chang, Cristóbal A. Navarro, Mauricio Cerda
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%.
no code implementations • 22 Feb 2023 • Cristian Muñoz, Sara Zannone, Umar Mohammed, Adriano Koshiyama
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.