CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research

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.

Cited by in corpus (32)

• Contextual Encoder-Decoder Network for Visual Saliency Prediction
• Faster gaze prediction with dense networks and Fisher pruning
• Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features
• Vanishing point detection with convolutional neural networks
• Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges
• State-of-the-Art in Human Scanpath Prediction
• Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset
• Psychophysical evaluation of individual low-level feature influences on visual attention
• A Dataset for Provident Vehicle Detection at Night
• Object category understanding via eye fixations on freehand sketches
• See, Attend and Brake: An Attention-based Saliency Map Prediction Model for End-to-End Driving
• Matching Representations of Explainable Artificial Intelligence and Eye Gaze for Human-Machine Interaction
• EyeNet: A Multi-Task Network for Off-Axis Eye Gaze Estimation and User Understanding
• A Comparative Study of Scanpath Models in Graph-Based Visualization
• Saliency for free: Saliency prediction as a side-effect of object recognition
• Saccade Sequence Prediction: Beyond Static Saliency Maps
• Visual Language Modeling on CNN Image Representations
• Scalable Plug-and-Play ADMM with Convergence Guarantees
• MagicEyes: A Large Scale Eye Gaze Estimation Dataset for Mixed Reality
• Wave Propagation of Visual Stimuli in Focus of Attention
• Saliency Preservation in Low-Resolution Grayscale Images
• Saliency Revisited: Analysis of Mouse Movements versus Fixations
• AiR: Attention with Reasoning Capability
• Visual Attention driven by Convolutional Features
• Light-weighted Saliency Detection with Distinctively Lower Memory Cost and Model Size
• Modeling Object Dissimilarity for Deep Saliency Prediction
• $n$-Reference Transfer Learning for Saliency Prediction
• Maps of Visual Importance
• Diptychs of human and machine perceptions
• Unsupervised Foveal Vision Neural Networks with Top-Down Attention
• EEG-Driven Image Reconstruction with Saliency-Guided Diffusion Models
• Model-guided Multi-path Knowledge Aggregation for Aerial Saliency Prediction