CertainNet: Sampling-Free Uncertainty Estimation for Object Detection

Gasperini S, Haug J, Mahani MAN, Marcos-Ramiro A, Navab N, Busam B, Tombari F (2022)

Publication Type: Journal article

Publication year: 2022

Journal

IEEE Robotics and Automation Letters IEEE

Book Volume: 7

Pages Range: 698-705

Journal Issue: 2

DOI: 10.1109/LRA.2021.3130976

Abstract

Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In perception for autonomous driving, measuring the uncertainty means providing additional calibrated information to downstream tasks, such as path planning, that can use it towards safe navigation. In this work, we propose a novel sampling-free uncertainty estimation method for object detection. We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size. To achieve this, we propose an uncertainty-aware heatmap, and exploit the neighboring bounding boxes provided by the detector at inference time. We evaluate the detection performance and the quality of the different uncertainty estimates separately, also with challenging out-of-domain samples: BDD100K and nuImages with models trained on KITTI. Additionally, we propose a new metric to evaluate location and size uncertainties. When transferring to unseen datasets, CertainNet generalizes substantially better than previous methods and an ensemble, while being real-time and providing high quality and comprehensive uncertainty estimates.

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) BMW AG - Bayerische Motoren Werke / BMW Group DE Germany (DE)

How to cite

APA:

Gasperini, S., Haug, J., Mahani, M.-A.N., Marcos-Ramiro, A., Navab, N., Busam, B., & Tombari, F. (2022). CertainNet: Sampling-Free Uncertainty Estimation for Object Detection. IEEE Robotics and Automation Letters, 7(2), 698-705. https://dx.doi.org/10.1109/LRA.2021.3130976

MLA:

Gasperini, Stefano, et al. "CertainNet: Sampling-Free Uncertainty Estimation for Object Detection." IEEE Robotics and Automation Letters 7.2 (2022): 698-705.

BibTeX: Download