A Trainable Feature Extractor Module for Deep Neural Networks and Scanpath Classification

TL;DR

This paper introduces a trainable feature extraction module for deep neural networks that transforms scanpaths into feature vectors, enhancing classification performance in eye tracking applications.

Contribution

It presents a novel, jointly trainable feature extraction module that adapts based on backpropagation, improving scanpath classification accuracy.

Findings

Outperforms state-of-the-art methods on three public datasets

Effectively adapts parameters during training for better feature representation

Integrates seamlessly with deep neural network architectures

Abstract

Scanpath classification is an area in eye tracking research with possible applications in medicine, manufacturing as well as training systems for students in various domains. In this paper we propose a trainable feature extraction module for deep neural networks. The purpose of this module is to transform a scanpath into a feature vector which is directly useable for the deep neural network architecture. Based on the backpropagated error of the deep neural network, the feature extraction module adapts its parameters to improve the classification performance. Therefore, our feature extraction module is jointly trainable with the deep neural network. The motivation to this feature extraction module is based on classical histogram-based approaches which usually compute distributions over a scanpath. We evaluated our module on three public datasets and compared it to the state of the art approaches.