# Learning data association without data association: An EM approach to neural assignment prediction

arXiv: https://arxiv.org/abs/2105.00369 · HTML: https://mlsanity.com/paper/2105.00369/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 17 references that are in the map.
- First posted on arXiv 2 May 2021.

## Builds on (most cited first, 4 of 4)

- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [Learning Latent Permutations with Gumbel-Sinkhorn Networks](https://mlsanity.com/paper/1802.08665/) (2018)
- [Simple Unsupervised Multi-Object Tracking](https://mlsanity.com/paper/2006.02609/) (2020)

## Built on by (most cited first, 1 of 1)

- [Learning of Global Objective for Network Flow in Multi-Object Tracking](https://mlsanity.com/paper/2203.16210/) (2022)

## Abstract (arXiv)

Data association is a fundamental component of effective multi-object tracking. Current approaches to data-association tend to frame this as an assignment problem relying on gating and distance-based cost matrices, or offset the challenge of data association to a problem of tracking by detection. The latter is typically formulated as a supervised learning problem, and requires labelling information about tracked object identities to train a model for object recognition. This paper introduces an expectation maximisation approach to train neural models for data association, which does not require labelling information. Here, a Sinkhorn network is trained to predict assignment matrices that maximise the marginal likelihood of trajectory observations. Importantly, networks trained using the proposed approach can be re-used in downstream tracking applications.