• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Assessing Box Merging Strategies and Uncertainty Estimation Methods in Multimodel Object Detection
 
  • Details
  • Full
Options
2020
Conference Paper
Titel

Assessing Box Merging Strategies and Uncertainty Estimation Methods in Multimodel Object Detection

Abstract
This paper examines the impact of different box merging strategies for sampling-based uncertainty estimation methods in object detection. Also, a comparison between the almost exclusively used softmax confidence scores and the predicted variances on the quality of the final predictions estimates is presented. The results suggest that estimated variances are a stronger predictor for the detection quality. However, variance-based merging strategies do not improve significantly over the confidence-based alternative for the given setup. In contrast, we show that different methods to estimate the uncertainty of the predictions have a significant influence on the quality of the ensembling outcome. Since mAP does not reward uncertainty estimates, such improvements were only noticeable on the resulting PDQ scores.
Author(s)
Schmoeller Roza, Felippe
Fraunhofer-Institut für Kognitive Systeme IKS
Henne, Maximilian
Fraunhofer-Institut für Kognitive Systeme IKS
Roscher, Karsten
Fraunhofer-Institut für Kognitive Systeme IKS
Günnemann, Stephan
Technische Univ. München, München
Hauptwerk
Computer Vision - ECCV 2020 Workshops. Proceedings. Pt.VI
Funder
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie StMWi
Konferenz
European Conference on Computer Vision (ECCV) 2020
Workshop "Beyond mAP - Reassessing the Evaluation of Object Detectors" 2020
DOI
10.1007/978-3-030-65414-6_1
File(s)
N-621463.pdf (567.23 KB)
Language
English
google-scholar
Fraunhofer-Institut für Kognitive Systeme IKS
Tags
  • uncertainty estimation

  • deep ensembles

  • object detection

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022