# Semi-supervised Vector-Quantization in Visual SLAM using HGCN

arXiv: https://arxiv.org/abs/2207.06738 · HTML: https://mlsanity.com/paper/2207.06738/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 49 references that are in the map.
- First posted on arXiv 14 Jul 2022.

## Builds on (most cited first, 11 of 11)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Hyperbolic Graph Convolutional Neural Networks](https://mlsanity.com/paper/1910.12933/) (2019)
- [Constant Curvature Graph Convolutional Networks](https://mlsanity.com/paper/1911.05076/) (2019)
- [Lorentzian Graph Convolutional Networks](https://mlsanity.com/paper/2104.07477/) (2021)
- [The Newer College Dataset: Handheld LiDAR, Inertial and Vision with Ground Truth](https://mlsanity.com/paper/2003.05691/) (2020)
- [iBoW-LCD: An Appearance-based Loop Closure Detection Approach using Incremental Bags of Binary Words](https://mlsanity.com/paper/1802.05909/) (2018)
- [OV2SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications](https://mlsanity.com/paper/2102.04060/) (2021)
- [An Efficient Index for Visual Search in Appearance-based SLAM](https://mlsanity.com/paper/1309.7170/) (2013)

## Abstract (arXiv)

In this paper, two semi-supervised appearance based loop closure detection technique, HGCN-FABMAP and HGCN-BoW are introduced. Furthermore an extension to the current state of the art localization SLAM algorithm, ORB-SLAM, is presented. The proposed HGCN-FABMAP method is implemented in an off-line manner incorporating Bayesian probabilistic schema for loop detection decision making. Specifically, we let a Hyperbolic Graph Convolutional Neural Network (HGCN) to operate over the SURF features graph space, and perform vector quantization part of the SLAM procedure. This part previously was performed in an unsupervised manner using algorithms like HKmeans, kmeans++,..etc. The main Advantage of using HGCN, is that it scales linearly in number of graph edges. Experimental results shows that HGCN-FABMAP algorithm needs far more cluster centroids than HGCN-ORB, otherwise it fails to detect loop closures. Therefore we consider HGCN-ORB to be more efficient in terms of memory consumption, also we conclude the superiority of HGCN-BoW and HGCN-FABMAP with respect to other algorithms.