CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research

By Ali Borji, Laurent Itti. arXiv.org, 2015

322 citations recorded by the source corpus.

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.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/519feb1f3c23baea6960dfa204521f96a74b82bb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Sensory Systems

Citations in the corpus

Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset (2019, background): “Examples include MIT saliency benchmark (Bylinskii et al. ), CAT2000 (Borji and Itti 2015), and SALICON (Jiang et al. 2015).”
DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations (2015, methodology): “We evaluate our network by testing on two datasets - CAT2000 [22], MIT300 [5].”
Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency (2021, methodology): “The model is trained on three publicly available external datasets: Borji and Itti [11], Jiang et al. [46], Judd et al. [47].”
Predicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model (2016, background): “We report results for both SAM-VGG and SAM-ResNet on SALICON [44] (plots a-d), MIT1003 [10] (plots e-h) and CAT2000 [61] (plots i-l) validation sets.”
Faster gaze prediction with dense networks and Fisher pruning (2018, methodology): “We used the publicly available CAT2000 [2] dataset for evaluation, which was not used during training of any of the models.”