Tuesday, June 26, 2018

MIT Benchmark puts Feng-GUI at the Forefront of Innovative Design

Massachusetts Institute of Technology (MIT), the best university of technology in the world, has reviewed the accuracy of Feng-GUI attention algorithm as part of its Saliency Benchmark.

Feng-GUI scores 83% similarity to predicted eye-tracking at the MIT CAT2000 test.
The baseline of the test is how humans predicts eye-tracking of other humans, and their score is 90%.
Using this scale, puts Feng-GUI at the score of 92% similarity to real eye-tracking.

The CAT2000 benchmark results page.
http://saliency.mit.edu/results_cat2000.html

About the benchmark
"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."

Ali Borji, Laurent Itti.
CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research
[CVPR 2015 workshop on "Future of Datasets"]

Tilke Judd, Fredo Durand, Antonio Torralba.
A Benchmark of Computational Models of Saliency to Predict Human Fixations [MIT tech report 2012]