# Adversarial Transfer of Pose Estimation Regression

arXiv: https://arxiv.org/abs/2006.11658 · HTML: https://mlsanity.com/paper/2006.11658/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2020.

## Built on by (most cited first, 4 of 4)

- [Reassessing the Limitations of CNN Methods for Camera Pose Regression](https://mlsanity.com/paper/2108.07260/) (2021)
- [A Critical Analysis of Image-based Camera Pose Estimation Techniques](https://mlsanity.com/paper/2201.05816/) (2022)
- [Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments](https://mlsanity.com/paper/2304.07250/) (2023)
- [Universal Domain Adaptation in Ordinal Regression](https://mlsanity.com/paper/2106.11576/) (2021)

## Abstract (arXiv)

We address the problem of camera pose estimation in visual localization. Current regression-based methods for pose estimation are trained and evaluated scene-wise. They depend on the coordinate frame of the training dataset and show a low generalization across scenes and datasets. We identify the dataset shift an important barrier to generalization and consider transfer learning as an alternative way towards a better reuse of pose estimation models. We revise domain adaptation techniques for classification and extend them to camera pose estimation, which is a multi-regression task. We develop a deep adaptation network for learning scene-invariant image representations and use adversarial learning to generate such representations for model transfer. We enrich the network with self-supervised learning and use the adaptability theory to validate the existence of scene-invariant representation of images in two given scenes. We evaluate our network on two public datasets, Cambridge Landmarks and 7Scene, demonstrate its superiority over several baselines and compare to the state of the art methods.