1 code implementation • 5 May 2020 • Deepak Mishra, Aravind Jayendran, Prathosh A. P
We derive from first principles, the necessary and sufficient conditions needed to achieve faithful clustering in the GAN framework: (i) presence of a multimodal latent space with adjustable priors, (ii) existence of a latent space inversion mechanism and (iii) imposition of the desired cluster priors on the latent space.
no code implementations • 10 Dec 2019 • Arnab Kumar Mondal, Sankalan Pal Chowdhury, Aravind Jayendran, Parag Singla, Himanshu Asnani, Prathosh AP
The field of neural generative models is dominated by the highly successful Generative Adversarial Networks (GANs) despite their challenges, such as training instability and mode collapse.
no code implementations • 8 Nov 2018 • Deepak Mishra, Prathosh A. P., Aravind Jayendran, Varun Srivastava, Santanu Chaudhury
Generative adversarial networks (GANs) have shown remarkable success in generation of unstructured data, such as, natural images.