Search Results for author: Andry Rasoanaivo

Found 3 papers, 3 papers with code

Learning meta-features for AutoML

1 code implementation • ICLR 2022 • Herilalaina Rakotoarison, Louisot Milijaona, Andry Rasoanaivo, Michele Sebag, Marc Schoenauer

This paper tackles the AutoML problem, aimed to automatically select an ML algorithm and its hyper-parameter configuration most appropriate to the dataset at hand.

AutoML

Paper
Code

Tarsier: Evolving Noise Injection in Super-Resolution GANs

1 code implementation • 25 Sep 2020 • Baptiste Roziere, Nathanal Carraz Rakotonirina, Vlad Hosu, Andry Rasoanaivo, Hanhe Lin, Camille Couprie, Olivier Teytaud

More generally, our approach can be used to optimize any method based on noise injection.

Image Super-Resolution

130

Paper
Code

ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network

1 code implementation • 21 Jan 2020 • Nathanaël Carraz Rakotonirina, Andry Rasoanaivo

Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is a perceptual-driven approach for single image super resolution that is able to produce photorealistic images.

Generative Adversarial Network Image Super-Resolution

130

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.