# Offline Auto Labeling: BAAS

arXiv: https://arxiv.org/abs/2508.09585 · HTML: https://mlsanity.com/paper/2508.09585/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 15 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 1 of 1)

- [Automated Ground Truth Estimation For Automotive Radar Tracking Applications With Portable GNSS And IMU Devices](https://mlsanity.com/paper/1905.11987/) (2019)

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

- [LEO: Graph Attention Network based Hybrid Multi Sensor Extended Object Fusion and Tracking for Autonomous Driving Applications](https://mlsanity.com/paper/2604.02206/) (2026)

## Abstract (arXiv)

This paper introduces BAAS, a new Extended Object Tracking (EOT) and fusion-based label annotation framework for radar detections in autonomous driving. Our framework utilizes Bayesian-based tracking, smoothing and eventually fusion methods to provide veritable and precise object trajectories along with shape estimation to provide annotation labels on the detection level under various supervision levels. Simultaneously, the framework provides evaluation of tracking performance and label annotation. If manually labeled data is available, each processing module can be analyzed independently or combined with other modules to enable closed-loop continuous improvements. The framework performance is evaluated in a challenging urban real-world scenario in terms of tracking performance and the label annotation errors. We demonstrate the functionality of the proposed approach for varying dynamic objects and class types