no code implementations • 8 Mar 2023 • Chenqi Guo, Fabian Benitez-Quiroz, Qianli Feng, Aleix Martinez
Our experiments on imbalanced image dataset classification show that, the validation accuracy improvement with such re-balancing method is related to the image similarity between different classes.
1 code implementation • ICCV 2021 • Qianli Feng, Chenqi Guo, Fabian Benitez-Quiroz, Aleix Martinez
With empirical evidence from BigGAN and StyleGAN2, on datasets CelebA, Flower and LSUN-bedroom, we show that dataset size and its complexity play an important role in GANs replication and perceptual quality of the generated images.
no code implementations • 30 Nov 2021 • Stuart Synakowski, Fabian Benitez-Quiroz, Aleix M. Martinez
Our newly developed practical topological characterization of DNNs allows for an additional set of applications.
1 code implementation • 12 Apr 2021 • Jeffrey Wen, Fabian Benitez-Quiroz, Qianli Feng, Aleix Martinez
Leveraging the learned structure of the latent space, we find moving in this direction corrects many image artifacts and brings the image into greater realism.