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

TL;DR

This paper introduces a human-in-the-loop method using active learning to extract interpretable visual concepts from deep neural networks, aiding model understanding and improving performance through targeted data augmentation.

Contribution

The paper presents a novel interactive system, ConceptExtract, that efficiently combines human feedback with active learning to identify meaningful concepts affecting model decisions.

Findings

Active learning accurately extracts visual concepts

Identified concepts that negatively impact performance

Data augmentation based on concepts improves model accuracy

Abstract

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-loop 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.