CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research

TL;DR

This paper introduces CAT2000, a large-scale eye-tracking dataset with 4000 images across 20 categories, designed to improve and evaluate saliency models and support behavioral studies in visual attention.

Contribution

The creation of a comprehensive, diverse fixation dataset with 4000 images across multiple categories to challenge and advance saliency modeling.

Findings

Dataset includes 120 observers' eye movements.

Comparison of successful models on the new dataset.

Analysis of basic properties of the dataset.

Abstract

Saliency modeling has been an active research area in computer vision for about two decades. Existing state of the art models perform very well in predicting where people look in natural scenes. There is, however, the risk that these models may have been overfitting themselves to available small scale biased datasets, thus trapping the progress in a local minimum. To gain a deeper insight regarding current issues in saliency modeling and to better gauge progress, we recorded eye movements of 120 observers while they freely viewed a large number of naturalistic and artificial images. Our stimuli includes 4000 images; 200 from each of 20 categories covering different types of scenes such as Cartoons, Art, Objects, Low resolution images, Indoor, Outdoor, Jumbled, Random, and Line drawings. We analyze some basic properties of this dataset and compare some successful models. We believe that our dataset opens new challenges for the next generation of saliency models and helps conduct behavioral studies on bottom-up visual attention.