ML Anthology

AutoDispNet: Improving Disparity Estimation with AutoML

Tonmoy Saikia, Yassine Marrakchi, Arber Zela, Frank Hutter, Thomas Brox
ICCV 2019
doi:10.1109/ICCV.2019.00190 /iccv/2019/saikia2019iccv-autodispnet/

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-scale compute cluster. We show results on disparity estimation that clearly outperform the manually optimized baseline and reach state-of-the-art performance.

PDF ICCV Semantic Scholar

Cite

Text

Saikia et al. "AutoDispNet: Improving Disparity Estimation with AutoML." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00190

Markdown

[Saikia et al. "AutoDispNet: Improving Disparity Estimation with AutoML." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/saikia2019iccv-autodispnet/) doi:10.1109/ICCV.2019.00190

BibTeX

@inproceedings{saikia2019iccv-autodispnet,
  title     = {{AutoDispNet: Improving Disparity Estimation with AutoML}},
  author    = {Saikia, Tonmoy and Marrakchi, Yassine and Zela, Arber and Hutter, Frank and Brox, Thomas},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00190},
  url       = {https://mlanthology.org/iccv/2019/saikia2019iccv-autodispnet/}
}