Object Detection as Probabilistic Set Prediction

03/15/2022
by   Georg Hess, et al.
0

Accurate uncertainty estimates are essential for deploying deep object detectors in safety-critical systems. The development and evaluation of probabilistic object detectors have been hindered by shortcomings in existing performance measures, which tend to involve arbitrary thresholds or limit the detector's choice of distributions. In this work, we propose to view object detection as a set prediction task where detectors predict the distribution over the set of objects. Using the negative log-likelihood for random finite sets, we present a proper scoring rule for evaluating and training probabilistic object detectors. The proposed method can be applied to existing probabilistic detectors, is free from thresholds, and enables fair comparison between architectures. Three different types of detectors are evaluated on the COCO dataset. Our results indicate that the training of existing detectors is optimized toward non-probabilistic metrics. We hope to encourage the development of new object detectors that can accurately estimate their own uncertainty. Code will be released.

READ FULL TEXT

page 2

page 6

page 8

page 14

page 21

page 22

page 23

research
01/13/2021

Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors

Predictive uncertainty estimation is an essential next step for the reli...
research
03/25/2021

USB: Universal-Scale Object Detection Benchmark

Benchmarks, such as COCO, play a crucial role in object detection. Howev...
research
04/03/2021

Uncertainty for Identifying Open-Set Errors in Visual Object Detection

Deployed into an open world, object detectors are prone to a type of fal...
research
10/06/2022

A Review of Uncertainty Calibration in Pretrained Object Detectors

In the field of deep learning based computer vision, the development of ...
research
04/12/2023

Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling

Deploying deep learning models in real-world certified systems requires ...
research
06/21/2019

Uncertainty in the Predictive Capability of Detectors that Process Waveforms from Explosions

Explosions near ground generate multiple geophysical waveforms in the ra...
research
11/27/2018

Probability-based Detection Quality (PDQ): A Probabilistic Approach to Detection Evaluation

We propose a new visual object detector evaluation measure which not onl...

Please sign up or login with your details

Forgot password? Click here to reset