Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 54 references that are in the map. First posted on arXiv 12 Apr 2023.
Builds on
18 of 54 references.
References · 18
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
- 2018Deep learning for time series classification: a reviewcited by 575
- 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
- 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
- 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
- 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
- 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
- 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
- 2021Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAycited by 53
- 2020Explainable Face Recognitioncited by 34
6 more
- 2021Interpretable Semantic Photo Geolocationcited by 32
- 2019Deep Eyedentification: Biometric Identification using Micro-Movements of the Eyecited by 25
- 2020GazeBase: A Large-Scale, Multi-Stimulus, Longitudinal Eye Movement Datasetcited by 20
- 2021Eye Know You: Metric Learning for End-to-end Biometric Authentication Using Eye Movements from a Longitudinal Datasetcited by 11
- 2022Detection of ADHD based on Eye Movements during Natural Viewingcited by 5
- 2023pymovements: A Python Package for Eye Movement Data Processingcited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.