papers AI Learner
The Github is limit! Click to go to the new site.

AutoDispNet: Improving Disparity Estimation with AutoML

2019-05-17
Tonmoy Saikia, Yassine Marrakchi, Arber Zela, Frank Hutter, Thomas Brox

Abstract

Much research work in computer vision is being spent on optimizing existing network architectures to obtain a few more percentage points on benchmarks. Recent AutoML approaches promise to relieve us from this effort. However, they are mainly designed for comparatively small-scale classification tasks. In this work, we show how to use and extend existing AutoML techniques to efficiently optimize large-scale U-Net-like encoder-decoder architectures. In particular, we leverage gradient-based neural architecture search and Bayesian optimization for hyperparameter search. The resulting optimization does not require a large company-scale compute cluster. We show results on disparity estimation that clearly outperform the manually optimized baseline and reach state-of-the-art performance.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.07443

PDF

http://arxiv.org/pdf/1905.07443


Similar Posts

Comments