计算机科学
人工智能
机器学习
深度学习
卷积神经网络
人工神经网络
模式识别(心理学)
可解释性
可视化
作者
Zhenge Zhao,Panpan Xu,Carlos Scheidegger,Liu Ren
出处
期刊:IEEE Transactions on Visualization and Computer Graphics
[Institute of Electrical and Electronics Engineers]
日期:2021-09-29
卷期号:: 1-1
标识
DOI:10.1109/tvcg.2021.3114837
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI