Learning User Embeddings from Human Gaze for Personalised Saliency Prediction

TL;DR

This paper introduces a novel method to derive user embeddings from limited eye tracking data, enhancing personalized saliency prediction without needing explicit user information.

Contribution

A new Siamese neural network approach to extract user embeddings from eye tracking data, improving personalization in saliency prediction without requiring explicit user characteristics.

Findings

Embeddings effectively discriminate between users.

Significantly improve personalized saliency maps.

Generalize well across different users and images.

Abstract

Reusable embeddings of user behaviour have shown significant performance improvements for the personalised saliency prediction task. However, prior works require explicit user characteristics and preferences as input, which are often difficult to obtain. We present a novel method to extract user embeddings from pairs of natural images and corresponding saliency maps generated from a small amount of user-specific eye tracking data. At the core of our method is a Siamese convolutional neural encoder that learns the user embeddings by contrasting the image and personal saliency map pairs of different users. Evaluations on two public saliency datasets show that the generated embeddings have high discriminative power, are effective at refining universal saliency maps to the individual users, and generalise well across users and images. Finally, based on our model's ability to encode individual user characteristics, our work points towards other applications that can benefit from reusable embeddings of gaze behaviour.