# AutoDispNet: Improving Disparity Estimation With AutoML

## TL;DR

AutoDispNet leverages AutoML techniques like gradient-based neural architecture search and Bayesian optimization to enhance disparity estimation, achieving state-of-the-art results without extensive computational resources.

## Contribution

This work extends AutoML methods to large-scale U-Net-like architectures for disparity estimation, demonstrating efficient optimization and superior performance.

## Key findings

- Outperforms manually optimized baselines in disparity estimation
- Achieves state-of-the-art performance on benchmark datasets
- Efficient AutoML approach requiring limited computational resources

## 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.