23 citations · 56 across the 9 of their papers we have counts for
9 papers
A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
Tomoki Watanabe, Paolo Favaro
We propose a novel GAN training scheme that can handle any level of labeling in a unified manner. Our scheme introduces a form of artificial labeling that can incorporate manually…
Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation
German Ros, Simon Stent, Pablo F. Alcantarilla +1
In this work we investigate the problem of road scene semantic segmentation using Deconvolutional Networks (DNs). Several constraints limit the practical performance of DNs in this…
Dirac-field model of inflation in Einstein-Cartan theory
Tomoki Watanabe
We present a cosmological model in which a single Dirac field with a flat potential can give rise to inflation within the framework of the Einstein-Cartan theory. It is shown that…
Angular Power Spectrum in Modular Invariant Inflation Model
Mitsuo J. Hayashi, Shiro Hirai, Tomoyuki Takami +3
We propose a scalar potential of inflation, motivated by modular invariant supergravity, and compute the angular power spectra of the adiabatic density perturbations that result fr…
Angular Power Spectrum and Dilatonic Inflation in Modular-Invariant Supergravity
Mitsuo J. Hayashi, Shiro Hirai, Yusuke Okame +1
The angular power spectrum is investigated in the model of supergravity, incorporating the target-space duality and the non-perturbative gaugino condensation in the hidden sector.…
Dilatonic Inflation and SUSY Breaking in Modular-Invariant Supergravity
Mitsuo J. Hayashi, Tomoki Watanabe
The theory of inflation will be investigated as well as supersymmetry breaking in the context of supergravity, incorporating the target-space duality and the non-perturbative gaugi…