Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models
This work provides a quantitative method for interpreting biometric models in eye tracking, but it is incremental as it builds on existing gaze event detection techniques.
The paper tackled the lack of quantitative analysis in explaining deep neural sequence models for eye tracking data by using gaze event detection to evaluate concept influence, finding that saccade features are substantially more important than fixation features, with samples near saccadic peak velocity being most influential.
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.