AutoDispNet: Improving Disparity Estimation With AutoML

被引：48

作者：

Saikia, Tonmoy ^{[1
]}

Marrakchi, Yassine ^{[1
]}

Zela, Arber ^{[1
]}

Hutter, Frank ^{[1
]}

Brox, Thomas ^{[1
]}

机构：

[1] Univ Freiburg, Freiburg, Germany

来源：

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) | 2019年

关键词：

NETWORKS;

D O I：

10.1109/ICCV.2019.00190

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：1812 / 1823

页数：12