Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models
arXiv:2304.13536 · doi:10.1145/3588015.3588412
Abstract
Recent work in XAI for eye tracking data has evaluated the suitability of feature attribution methods to explain the output of deep neural sequence models for the task of oculomotric biometric identification. These methods provide saliency maps to highlight important input features of a specific eye gaze sequence. However, to date, its localization analysis has been lacking a quantitative approach across entire datasets. In this work, we employ established gaze event detection algorithms for fixations and saccades and quantitatively evaluate the impact of these events by determining their concept influence. Input features that belong to saccades are shown to be substantially more important than features that belong to fixations. By dissecting saccade events into sub-events, we are able to show that gaze samples that are close to the saccadic peak velocity are most influential. We further investigate the effect of event properties like saccadic amplitude or fixational dispersion on the resulting concept influence.
arXiv commentPreprint for ETRA '23: 2023 Symposium on Eye Tracking Research and Applications
References in corpus (12)
- Scikit-learn: Machine Learning in Python
- Deep learning for time series classification: a review
- Axiomatic Attribution for Deep Networks
- Methods for Interpreting and Understanding Deep Neural Networks
- Learning Important Features Through Propagating Activation Differences
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Captum: A unified and generic model interpretability library for PyTorch
- Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
- Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
- Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy
- pymovements: A Python Package for Eye Movement Data Processing
- Eye Know You: Metric Learning for End-to-end Biometric Authentication Using Eye Movements from a Longitudinal Dataset