Calibrating Uncertainties in Object Localization Task

11/27/2018
by   Buu Phan, et al.
0

In many safety-critical applications such as autonomous driving and surgical robots, it is desirable to obtain prediction uncertainties from object detection modules to help support safe decision-making. Specifically, such modules need to estimate the probability of each predicted object in a given region and the confidence interval for its bounding box. While recent Bayesian deep learning methods provide a principled way to estimate this uncertainty, the estimates for the bounding boxes obtained using these methods are uncalibrated. In this paper, we address this problem for the single-object localization task by adapting an existing technique for calibrating regression models. We show, experimentally, that the resulting calibrated model obtains more reliable uncertainty estimates.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2019

Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving

Reliable uncertainty estimation is crucial for perception systems in saf...
research
10/04/2021

CertainNet: Sampling-free Uncertainty Estimation for Object Detection

Estimating the uncertainty of a neural network plays a fundamental role ...
research
06/22/2020

Towards Better Performance and More Explainable Uncertainty for 3D Object Detection of Autonomous Vehicles

In this paper, we propose a novel form of the loss function to increase ...
research
11/08/2022

Calibrated Perception Uncertainty Across Objects and Regions in Bird's-Eye-View

In driving scenarios with poor visibility or occlusions, it is important...
research
03/06/2023

EvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learning

Uncertainty estimation is crucial in safety-critical settings such as au...
research
06/28/2020

Localization Uncertainty Estimation for Anchor-Free Object Detection

Since many safety-critical systems such as surgical robots and autonomou...
research
10/04/2020

MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection

In object detection with deep neural networks, the box-wise objectness s...

Please sign up or login with your details

Forgot password? Click here to reset