Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.05006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911194109968384 |
|---|---|
| author | Vellenga, Koen Steinhauer, H. Joe Andersson, Jonas Sjögren, Anders |
| author_facet | Vellenga, Koen Steinhauer, H. Joe Andersson, Jonas Sjögren, Anders |
| contents | Deep neural networks (DNNs) are increasingly applied to safety-critical tasks in resource-constrained environments, such as video-based driver action and intention recognition. While last layer probabilistic deep learning (LL-PDL) methods can detect out-of-distribution (OOD) instances, their performance varies. As an alternative to last layer approaches, we propose extending pre-trained DNNs with transformation layers to produce multiple latent representations to estimate the uncertainty. We evaluate our latent uncertainty representation (LUR) and repulsively trained LUR (RLUR) approaches against eight PDL methods across four video-based driver action and intention recognition datasets, comparing classification performance, calibration, and uncertainty-based OOD detection. We also contribute 28,000 frame-level action labels and 1,194 video-level intention labels for the NuScenes dataset. Our results show that LUR and RLUR achieve comparable in-distribution classification performance to other LL-PDL approaches. For uncertainty-based OOD detection, LUR matches top-performing PDL methods while being more efficient to train and easier to tune than approaches that require Markov-Chain Monte Carlo sampling or repulsive training procedures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_05006 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Latent Uncertainty Representations for Video-based Driver Action and Intention Recognition Vellenga, Koen Steinhauer, H. Joe Andersson, Jonas Sjögren, Anders Computer Vision and Pattern Recognition Machine Learning Deep neural networks (DNNs) are increasingly applied to safety-critical tasks in resource-constrained environments, such as video-based driver action and intention recognition. While last layer probabilistic deep learning (LL-PDL) methods can detect out-of-distribution (OOD) instances, their performance varies. As an alternative to last layer approaches, we propose extending pre-trained DNNs with transformation layers to produce multiple latent representations to estimate the uncertainty. We evaluate our latent uncertainty representation (LUR) and repulsively trained LUR (RLUR) approaches against eight PDL methods across four video-based driver action and intention recognition datasets, comparing classification performance, calibration, and uncertainty-based OOD detection. We also contribute 28,000 frame-level action labels and 1,194 video-level intention labels for the NuScenes dataset. Our results show that LUR and RLUR achieve comparable in-distribution classification performance to other LL-PDL approaches. For uncertainty-based OOD detection, LUR matches top-performing PDL methods while being more efficient to train and easier to tune than approaches that require Markov-Chain Monte Carlo sampling or repulsive training procedures. |
| title | Latent Uncertainty Representations for Video-based Driver Action and Intention Recognition |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2510.05006 |