1 code implementation • 26 Oct 2019 • Marcos Pividori, Guillermo L. Grinblat, Lucas C. Uzal
Finally, as an example of potential applications that arise from this inversion mechanism, we show preliminary results in exploiting the learned representation in the attention map of the generator to obtain an unsupervised segmentation of natural images.
1 code implementation • 21 Sep 2017 • Guillermo L. Grinblat, Lucas C. Uzal, Pablo M. Granitto
Generative Adversarial Networks (GANs) produce systematically better quality samples when class label information is provided., i. e. in the conditional GAN setup.
Ranked #8 on Conditional Image Generation on CIFAR-10 (Inception score metric)