# Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware

arXiv: https://arxiv.org/abs/2108.02671 · HTML: https://mlsanity.com/paper/2108.02671/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 5 Aug 2021.

## Builds on (most cited first, 23 of 23)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Virtual KITTI 2](https://mlsanity.com/paper/2001.10773/) (2020)
- [Domain Adaptation for Visual Applications: A Comprehensive Survey](https://mlsanity.com/paper/1702.05374/) (2017)
- [FastDepth: Fast Monocular Depth Estimation on Embedded Systems](https://mlsanity.com/paper/1903.03273/) (2019)
- [T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks](https://mlsanity.com/paper/1808.01454/) (2018)
- [Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation](https://mlsanity.com/paper/1904.01870/) (2019)
- [AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation](https://mlsanity.com/paper/1803.01599/) (2018)
- [Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints](https://mlsanity.com/paper/1905.04753/) (2019)
- [SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems](https://mlsanity.com/paper/1909.09709/) (2019)
- [Towards real-time unsupervised monocular depth estimation on CPU](https://mlsanity.com/paper/1806.11430/) (2018)
- [Traffic Control Gesture Recognition for Autonomous Vehicles](https://mlsanity.com/paper/2007.16072/) (2020)
- [Real-time single image depth perception in the wild with handheld devices](https://mlsanity.com/paper/2006.05724/) (2020)
- [Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets](https://mlsanity.com/paper/1901.02000/) (2019)
- [Binary DAD-Net: Binarized Driveable Area Detection Network for Autonomous Driving](https://mlsanity.com/paper/2006.08178/) (2020)
- [Adversarial Network Compression](https://mlsanity.com/paper/1803.10750/) (2018)

## Built on by (most cited first, 3 of 3)

- [Lightweight Monocular Depth Estimation through Guided Decoding](https://mlsanity.com/paper/2203.04206/) (2022)
- [A Survey on RGB-D Datasets](https://mlsanity.com/paper/2201.05761/) (2022)
- [Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation](https://mlsanity.com/paper/2405.17704/) (2024)

## Abstract (arXiv)

Real-world perception systems in many cases build on hardware with limited resources to adhere to cost and power limitations of their carrying system. Deploying deep neural networks on resource-constrained hardware became possible with model compression techniques, as well as efficient and hardware-aware architecture design. However, model adaptation is additionally required due to the diverse operation environments. In this work, we address the problem of training deep neural networks on resource-constrained hardware in the context of visual domain adaptation. We select the task of monocular depth estimation where our goal is to transform a pre-trained model to the target's domain data. While the source domain includes labels, we assume an unlabelled target domain, as it happens in real-world applications. Then, we present an adversarial learning approach that is adapted for training on the device with limited resources. Since visual domain adaptation, i.e. neural network training, has not been previously explored for resource-constrained hardware, we present the first feasibility study for image-based depth estimation. Our experiments show that visual domain adaptation is relevant only for efficient network architectures and training sets at the order of a few hundred samples. Models and code are publicly available.