# Deep Weakly Supervised Positioning

arXiv: https://arxiv.org/abs/2104.04866 · HTML: https://mlsanity.com/paper/2104.04866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 10 Apr 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (2017)
- [Learning Less is More - 6D Camera Localization via 3D Surface Regression](https://mlsanity.com/paper/1711.10228/) (2017)
- [On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location](https://mlsanity.com/paper/2003.07064/) (2020)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning](https://mlsanity.com/paper/1709.06841/) (2017)
- [A Survey of Indoor Localization Systems and Technologies](https://mlsanity.com/paper/1709.01015/) (2017)
- [Label-Free Supervision of Neural Networks with Physics and Domain Knowledge](https://mlsanity.com/paper/1609.05566/) (2016)
- [Image-based Localization using Hourglass Networks](https://mlsanity.com/paper/1703.07971/) (2017)
- [VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry](https://mlsanity.com/paper/1804.08366/) (2018)
- [VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization](https://mlsanity.com/paper/1702.06521/) (2017)
- [Semantic Visual Localization](https://mlsanity.com/paper/1712.05773/) (2017)
- [SegMatch: Segment based loop-closure for 3D point clouds](https://mlsanity.com/paper/1609.07720/) (2016)
- [SegMap: 3D Segment Mapping using Data-Driven Descriptors](https://mlsanity.com/paper/1804.09557/) (2018)
- [DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds](https://mlsanity.com/paper/1811.11397/) (2018)
- [Random Forests versus Neural Networks - What's Best for Camera Localization?](https://mlsanity.com/paper/1609.05797/) (2016)
- [DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network](https://mlsanity.com/paper/1910.11088/) (2019)
- [EMPNet: Neural Localisation and Mapping Using Embedded Memory Points](https://mlsanity.com/paper/1907.13268/) (2019)
- [Towards Visual Ego-motion Learning in Robots](https://mlsanity.com/paper/1705.10279/) (2017)
- [Learning by Inertia: Self-supervised Monocular Visual Odometry for Road Vehicles](https://mlsanity.com/paper/1905.01634/) (2019)

## Abstract (arXiv)

PoseNet can map a photo to the position where it is taken, which is appealing in robotics. However, training PoseNet requires full supervision, where ground truth positions are non-trivial to obtain. Can we train PoseNet without knowing the ground truth positions for each observation? We show that this is possible via constraint-based weak-supervision, leading to the proposed framework: DeepGPS. Particularly, using wheel-encoder-estimated distances traveled by a robot along random straight line segments as constraints between PoseNet outputs, DeepGPS can achieve a relative positioning error of less than 2%. Moreover, training DeepGPS can be done as auto-calibration with almost no human attendance, which is more attractive than its competing methods that typically require careful and expert-level manual calibration. We conduct various experiments on simulated and real datasets to demonstrate the general applicability, effectiveness, and accuracy of DeepGPS, and perform a comprehensive analysis of its robustness. Our code is available at https://ai4ce.github.io/DeepGPS/.