# Variational Voxel Pseudo Image Tracking

arXiv: https://arxiv.org/abs/2302.05914 · HTML: https://mlsanity.com/paper/2302.05914/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 12 Feb 2023.

## Builds on (most cited first, 30 of 30)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Randomized Prior Functions for Deep Reinforcement Learning](https://mlsanity.com/paper/1806.03335/) (2018)
- [LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving](https://mlsanity.com/paper/1903.08701/) (2019)
- [Epistemic Neural Networks](https://mlsanity.com/paper/2107.08924/) (2021)
- [A General Framework for Uncertainty Estimation in Deep Learning](https://mlsanity.com/paper/1907.06890/) (2019)
- [A Novel Performance Evaluation Methodology for Single-Target Trackers](https://mlsanity.com/paper/1503.01313/) (2015)
- [Learning to Track at 100 FPS with Deep Regression Networks](https://mlsanity.com/paper/1604.01802/) (2016)
- [P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds](https://mlsanity.com/paper/2005.13888/) (2020)
- [Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection](https://mlsanity.com/paper/1804.05132/) (2018)
- [Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2108.04728/) (2021)
- [PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2108.06455/) (2021)
- [3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud](https://mlsanity.com/paper/2108.05630/) (2021)
- [Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation](https://mlsanity.com/paper/1810.07884/) (2018)
- [Uncertainty Estimation in One-Stage Object Detection](https://mlsanity.com/paper/1905.10296/) (2019)
- [Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification](https://mlsanity.com/paper/1910.08168/) (2019)
- [Learning an Uncertainty-Aware Object Detector for Autonomous Driving](https://mlsanity.com/paper/1910.11375/) (2019)
- [Real-time 3D Single Object Tracking with Transformer](https://mlsanity.com/paper/2209.00860/) (2022)
- [Bayesian Learning for Neural Networks: an algorithmic survey](https://mlsanity.com/paper/2211.11865/) (2022)
- [Efficient Bird Eye View Proposals for 3D Siamese Tracking](https://mlsanity.com/paper/1903.10168/) (2019)
- [Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss](https://mlsanity.com/paper/2011.02553/) (2020)
- [Variational Neural Networks](https://mlsanity.com/paper/2207.01524/) (2022)
- [Uncertainty-aware Self-supervised 3D Data Association](https://mlsanity.com/paper/2008.08173/) (2020)
- [VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images](https://mlsanity.com/paper/2206.02619/) (2022)

## Abstract (arXiv)

Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and signaling the model's certainty in its predictions to the decision method or a human supervisor. In this paper, we propose a Variational Neural Network-based version of a Voxel Pseudo Image Tracking (VPIT) method for 3D Single Object Tracking. The Variational Feature Generation Network of the proposed Variational VPIT computes features for target and search regions and the corresponding uncertainties, which are later combined using an uncertainty-aware cross-correlation module in one of two ways: by computing similarity between the corresponding uncertainties and adding it to the regular cross-correlation values, or by penalizing the uncertain feature channels to increase influence of the certain features. In experiments, we show that both methods improve tracking performance, while penalization of uncertain features provides the best uncertainty quality.