Enhancing Eye Feature Estimation from Event Data Streams through Adaptive Inference State Space Modeling

TL;DR

This paper introduces AISSM, an adaptive model for eye feature extraction from event data that dynamically balances current and recent information, improving accuracy and efficiency.

Contribution

The paper presents a novel adaptive inference model with a dynamic confidence network for improved event-based eye feature extraction.

Findings

AISSM outperforms state-of-the-art models in eye feature extraction tasks.

The dynamic confidence network effectively estimates signal-to-noise ratio and event density.

The proposed learning technique enhances training efficiency.

Abstract

Eye feature extraction from event-based data streams can be performed efficiently and with low energy consumption, offering great utility to real-world eye tracking pipelines. However, few eye feature extractors are designed to handle sudden changes in event density caused by the changes between gaze behaviors that vary in their kinematics, leading to degraded prediction performance. In this work, we address this problem by introducing the adaptive inference state space model (AISSM), a novel architecture for feature extraction that is capable of dynamically adjusting the relative weight placed on current versus recent information. This relative weighting is determined via estimates of the signal-to-noise ratio and event density produced by a complementary dynamic confidence network. Lastly, we craft and evaluate a novel learning technique that improves training efficiency. Experimental results demonstrate that the AISSM system outperforms state-of-the-art models for event-based eye feature extraction.