• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. From Black-box to White-box: Examining Confidence Calibration under different Conditions
 
  • Details
  • Full
Options
2021
Conference Paper
Title

From Black-box to White-box: Examining Confidence Calibration under different Conditions

Abstract
Confidence calibration is a major concern when applying artificial neural networks in safety-critical applications. Since most research in this area has focused on classification in the past, confidence calibration in the scope of object detection has gained more attention only recently. Based on previous work, we study the miscalibration of object detection models with respect to image location and box scale. Our main contribution is to additionally consider the impact of box selection methods like non-maximum suppression to calibration. We investigate the default intrinsic calibration of object detection models and how it is affected by these post-processing techniques. For this purpose, we distinguish between black-box calibration with non-maximum suppression and white-box calibration with raw network outputs. Our experiments reveal that post-processing highly affects confidence calibration. We show that non-maximum suppression has the potential to degrade initially well-calibrated predictions, leading to overconfident and thus miscalibrated models.
Author(s)
Schwaiger, Franziska  
Fraunhofer-Institut für Kognitive Systeme IKS  
Henne, Maximilian
Fraunhofer-Institut für Kognitive Systeme IKS  
Küppers, Fabian
Hochschule Ruhr West, Bottrop
Schmoeller Roza, Felippe
Fraunhofer-Institut für Kognitive Systeme IKS  
Roscher, Karsten  
Fraunhofer-Institut für Kognitive Systeme IKS  
Haselhoff, Anselm
Hochschule Ruhr West, Bottrop
Mainwork
Workshop on Artificial Intelligence Safety, SafeAI 2021. Proceedings. Online resource  
Funder
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie StMWi  
Conference
Workshop on Artificial Intelligence Safety (SafeAI) 2021  
Conference on Artificial Intelligence (AAAI) 2021  
Open Access
File(s)
Download (3.16 MB)
Rights
CC BY 4.0: Creative Commons Attribution
DOI
10.24406/publica-fhg-410557
Language
English
Fraunhofer-Institut für Kognitive Systeme IKS  
Keyword(s)
  • calibration

  • neural networks

  • object recognition

  • safety engineering

  • safety critical

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024