Yao, Linghong;
Hadjivelichkov, Denis;
Delfaki, Andromachi Maria;
Liu, Yuanchang;
Paige, Brooks;
Kanoulas, Dimitrios;
(2024)
Balancing Calibration and Performance: Stochastic Depth in Segmentation BNNs.
In:
35th British Machine Vision Conference 2024, BMVC 2024.
BMVA: Glasgow, UK.
Preview |
PDF
Balancing Calibration and Performance - Stochastic Depth in Segmentation BNNs..pdf - Published Version Download (3MB) | Preview |
Abstract
In many safety-critical applications, it is critical for computer vision models to provide reliable uncertainty estimates. However, traditional Bayesian approaches often compromise between efficiency and safety. In this work, we introduce a novel implementation of stochastic depth within segmentation Bayesian Neural Networks (BNNs) that preserves performance while significantly improving uncertainty calibration. We experimentally validate our approach using an encoder-decoder model specifically tailored for real-time robotic vision tasks which demand fast and reliable decision-making under inherently uncertain conditions. Our method facilitates both safer and more effective deployment without compromises, increasing uncertainty calibration error whilst maintaining high performance.
| Type: | Proceedings paper |
|---|---|
| Title: | Balancing Calibration and Performance: Stochastic Depth in Segmentation BNNs |
| Event: | BMVC 2024 - 35th British Machine Vision Conference |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://bmvc2024.org/proceedings/546/ |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10211001 |
Archive Staff Only
 |
View Item |
