# Multi-Target Tracking with Transferable Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2210.15539 · HTML: https://mlsanity.com/paper/2210.15539/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 30 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [Next Generation Multitarget Trackers: Random Finite Set Methods vs Transformer-based Deep Learning](https://mlsanity.com/paper/2104.00734/) (2021)
- [Multi-sensor Joint Adaptive Birth Sampler for Labeled Random Finite Set Tracking](https://mlsanity.com/paper/2109.04355/) (2021)
- [Can Deep Learning be Applied to Model-Based Multi-Object Tracking?](https://mlsanity.com/paper/2202.07909/) (2022)

## Built on by (most cited first, 3 of 3)

- [Solving Large-scale Spatial Problems with Convolutional Neural Networks](https://mlsanity.com/paper/2306.08191/) (2023)
- [Transferability of Convolutional Neural Networks in Stationary Learning Tasks](https://mlsanity.com/paper/2307.11588/) (2023)
- [Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning](https://mlsanity.com/paper/2409.19829/) (2024)

## Abstract (arXiv)

Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning perspective and propose a convolutional neural network (CNN) architecture to tackle it. We represent the target states and sensor measurements as images and recast the problem as an image-to-image prediction task. Then we train a fully convolutional model at small tracking areas and transfer it to much larger areas with numerous targets and sensors. This transfer learning approach enables MTT at a large scale and is also theoretically supported by our novel analysis that bounds the generalization error. In practice, the proposed transferable CNN architecture outperforms random finite set filters on the MTT task with 10 targets and transfers without re-training to a larger MTT task with 250 targets with a 29% performance improvement.