• 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. Concept Correlation and its Effects on Concept-Based Models
 
  • Details
  • Full
Options
2023
Conference Paper
Title

Concept Correlation and its Effects on Concept-Based Models

Abstract
Concept-based learning approaches for image classification, such as Concept Bottleneck Models, aim to enable interpretation and increase robustness by directly learning high-level concepts which are used for predicting the main class. They achieve competitive test accuracies compared to standard end-to-end models. However, with multiple concepts per image and binary concept annotations (without concept localization), it is not evident if the output of the concept model is truly based on the predicted concepts or other features in the image. Additionally, high correlations between concepts would allow a model to predict a concept with high test accuracy by simply using a correlated concept as a proxy. In this paper, we analyze these correlations between concepts in the CUB and GTSRB datasets and propose methods beyond test accuracy for evaluating their effects on the performance of a concept-based model trained on this data. To this end, we also perform a more detailed analysis on the effects of concept correlation using synthetically generated datasets of 3D shapes. We see that high concept correlation increases the risk of a model's inability to distinguish these concepts. Yet simple techniques, like loss weighting, show promising initial results for mitigating this issue.
Author(s)
Heidemann, Lena  
Fraunhofer-Institut für Kognitive Systeme IKS  
Monnet, Maureen
Fraunhofer-Institut für Kognitive Systeme IKS  
Roscher, Karsten  
Fraunhofer-Institut für Kognitive Systeme IKS  
Mainwork
IEEE Winter Conference on Applications of Computer Vision, WACV 2023. Proceedings  
Project(s)
IKS-Ausbauprojekt  
Funder
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie  
Conference
Winter Conference on Applications of Computer Vision 2023  
Open Access
DOI
10.1109/WACV56688.2023.00476
10.24406/publica-876
File(s)
Download (427.22 KB)
Rights
Under Copyright
Language
English
Fraunhofer-Institut für Kognitive Systeme IKS  
Fraunhofer Group
Fraunhofer-Verbund IUK-Technologie  
Keyword(s)
  • Machine Learning

  • ML

  • Deep Neural Networks

  • DNN

  • artificial intelligence

  • AI

  • explainable artificial intelligence

  • explainable AI

  • interpretable model

  • concept bottleneck model

  • concept model

  • concept correlation

  • safe artificial intelligence

  • safe AI

  • safe machine learning

  • safe ML

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