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-scale compute cluster. We show results on disparity estimation that clearly outperform the manually optimized baseline and reach state-of-the-art performance.
@article{arxiv.1905.07443,
title = {AutoDispNet: Improving Disparity Estimation With AutoML},
author = {Tonmoy Saikia and Yassine Marrakchi and Arber Zela and Frank Hutter and Thomas Brox},
journal= {arXiv preprint arXiv:1905.07443},
year = {2019}
}
Comments
In Proceedings of the 2019 IEEE International Conference on Computer Vision (ICCV)