Human-in-The-loop Extraction of Interpretable Concepts in Deep Learning Models

Zhenge Zhao, Panpan Xu, Carlos Scheidegger, Liu Ren

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


The interpretation of deep neural networks (DNNs) has become a key topic as more and more people apply them to solve various problems and making critical decisions. Concept-based explanations have recently become a popular approach for post-hoc interpretation of DNNs. However, identifying human-understandable visual concepts that affect model decisions is a challenging task that is not easily addressed with automatic approaches. We present a novel human-in-The-Ioop approach to generate user-defined concepts for model interpretation and diagnostics. Central to our proposal is the use of active learning, where human knowledge and feedback are combined to train a concept extractor with very little human labeling effort. We integrate this process into an interactive system, ConceptExtract. Through two case studies, we show how our approach helps analyze model behavior and extract human-friendly concepts for different machine learning tasks and datasets and how to use these concepts to understand the predictions, compare model performance and make suggestions for model refinement. Quantitative experiments show that our active learning approach can accurately extract meaningful visual concepts. More importantly, by identifying visual concepts that negatively affect model performance, we develop the corresponding data augmentation strategy that consistently improves model performance.

Original languageEnglish (US)
Pages (from-to)780-790
Number of pages11
JournalIEEE Transactions on Visualization and Computer Graphics
Issue number1
StatePublished - Jan 1 2022


  • Deep Neural Network
  • Explainable AI
  • Model Interpretation
  • Visual Data Exploration

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Human-in-The-loop Extraction of Interpretable Concepts in Deep Learning Models'. Together they form a unique fingerprint.

Cite this