# Can Transformer Attention Spread Give Insights Into Uncertainty of Detected and Tracked Objects?

arXiv: https://arxiv.org/abs/2210.14391 · HTML: https://mlsanity.com/paper/2210.14391/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 15 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [A General Framework for Uncertainty Estimation in Deep Learning](https://mlsanity.com/paper/1907.06890/) (2019)
- [Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection](https://mlsanity.com/paper/1804.05132/) (2018)
- [Probabilistic 3D Multi-Object Tracking for Autonomous Driving](https://mlsanity.com/paper/2001.05673/) (2020)
- [Transformers for Multi-Object Tracking on Point Clouds](https://mlsanity.com/paper/2205.15730/) (2022)
- [Capturing Object Detection Uncertainty in Multi-Layer Grid Maps](https://mlsanity.com/paper/1901.11284/) (2019)
- [Transformers for Object Detection in Large Point Clouds](https://mlsanity.com/paper/2209.15258/) (2022)

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

- [ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers](https://mlsanity.com/paper/2604.22841/) (2026)

## Abstract (arXiv)

Transformers have recently been utilized to perform object detection and tracking in the context of autonomous driving. One unique characteristic of these models is that attention weights are computed in each forward pass, giving insights into the model's interior, in particular, which part of the input data it deemed interesting for the given task. Such an attention matrix with the input grid is available for each detected (or tracked) object in every transformer decoder layer. In this work, we investigate the distribution of these attention weights: How do they change through the decoder layers and through the lifetime of a track? Can they be used to infer additional information about an object, such as a detection uncertainty? Especially in unstructured environments, or environments that were not common during training, a reliable measure of detection uncertainty is crucial to decide whether the system can still be trusted or not.