Uncertainty in Real-Time Semantic Segmentation on Embedded Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915916762054656 |
|---|---|
| author | Goan, Ethan Fookes, Clinton |
| author_facet | Goan, Ethan Fookes, Clinton |
| contents | Application for semantic segmentation models in areas such as autonomous vehicles and human computer interaction require real-time predictive capabilities. The challenges of addressing real-time application is amplified by the need to operate on resource constrained hardware. Whilst development of real-time methods for these platforms has increased, these models are unable to sufficiently reason about uncertainty present when applied on embedded real-time systems. This paper addresses this by combining deep feature extraction from pre-trained models with Bayesian regression and moment propagation for uncertainty aware predictions. We demonstrate how the proposed method can yield meaningful epistemic uncertainty on embedded hardware in real-time whilst maintaining predictive performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_01201 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Uncertainty in Real-Time Semantic Segmentation on Embedded Systems Goan, Ethan Fookes, Clinton Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Application for semantic segmentation models in areas such as autonomous vehicles and human computer interaction require real-time predictive capabilities. The challenges of addressing real-time application is amplified by the need to operate on resource constrained hardware. Whilst development of real-time methods for these platforms has increased, these models are unable to sufficiently reason about uncertainty present when applied on embedded real-time systems. This paper addresses this by combining deep feature extraction from pre-trained models with Bayesian regression and moment propagation for uncertainty aware predictions. We demonstrate how the proposed method can yield meaningful epistemic uncertainty on embedded hardware in real-time whilst maintaining predictive performance. |
| title | Uncertainty in Real-Time Semantic Segmentation on Embedded Systems |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2301.01201 |