Home
Uni-Logo
 

AutoDispNet: Improving Disparity Estimation With AutoML

IEEE International Conference on Computer Vision (ICCV), 2019
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.
Paper

Images and movies

 

BibTex reference

@InProceedings{SMB19,
  author       = "T. Saikia and Y. Marrakchi and A. Zela and F. Hutter and T. Brox",
  title        = "AutoDispNet: Improving Disparity Estimation With AutoML",
  booktitle    = "IEEE International Conference on Computer Vision (ICCV)",
  month        = " ",
  year         = "2019",
  url          = "http://lmbweb.informatik.uni-freiburg.de/Publications/2019/SMB19"
}

Other publications in the database