Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914814252548096 |
|---|---|
| author | El-Ghoussani, Amir Hornauer, Julia Carneiro, Gustavo Belagiannis, Vasileios |
| author_facet | El-Ghoussani, Amir Hornauer, Julia Carneiro, Gustavo Belagiannis, Vasileios |
| contents | In monocular depth estimation, unsupervised domain adaptation has recently been explored to relax the dependence on large annotated image-based depth datasets. However, this comes at the cost of training multiple models or requiring complex training protocols. We formulate unsupervised domain adaptation for monocular depth estimation as a consistency-based semi-supervised learning problem by assuming access only to the source domain ground truth labels. To this end, we introduce a pairwise loss function that regularises predictions on the source domain while enforcing perturbation consistency across multiple augmented views of the unlabelled target samples. Importantly, our approach is simple and effective, requiring only training of a single model in contrast to the prior work. In our experiments, we rely on the standard depth estimation benchmarks KITTI and NYUv2 to demonstrate state-of-the-art results compared to related approaches. Furthermore, we analyse the simplicity and effectiveness of our approach in a series of ablation studies. The code is available at \url{https://github.com/AmirMaEl/SemiSupMDE}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17704 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation El-Ghoussani, Amir Hornauer, Julia Carneiro, Gustavo Belagiannis, Vasileios Computer Vision and Pattern Recognition In monocular depth estimation, unsupervised domain adaptation has recently been explored to relax the dependence on large annotated image-based depth datasets. However, this comes at the cost of training multiple models or requiring complex training protocols. We formulate unsupervised domain adaptation for monocular depth estimation as a consistency-based semi-supervised learning problem by assuming access only to the source domain ground truth labels. To this end, we introduce a pairwise loss function that regularises predictions on the source domain while enforcing perturbation consistency across multiple augmented views of the unlabelled target samples. Importantly, our approach is simple and effective, requiring only training of a single model in contrast to the prior work. In our experiments, we rely on the standard depth estimation benchmarks KITTI and NYUv2 to demonstrate state-of-the-art results compared to related approaches. Furthermore, we analyse the simplicity and effectiveness of our approach in a series of ablation studies. The code is available at \url{https://github.com/AmirMaEl/SemiSupMDE}. |
| title | Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.17704 |