The MIT/Tuebingen Saliency Benchmark is the sucessor of the MIT Saliency Benchmark and aims at advancing our understanding of what drives human eye movements. The benchmark hosts the MIT300 and the CAT2000 datasets for saliency model evaluation.
The main extension compared to the classic MIT Saliency Benchmark is that it now allows submission of models either as classic saliency maps (as in the past), or as fixation densities. The new prefered way of evaluating models is via the submission of probabilistic models predicting fixation densities. From those densities, metric-specific saliency maps can be derived which make model evaluation much more consistent. In nearly all cases, models perform better than with the classic evaluation since penalties due to saliency maps not matching the metrics are removed.
@misc{mit-tuebingen-saliency-benchmark,
author = {Matthias Kümmerer and Zoya Bylinskii and Tilke Judd and Ali Borji and Laurent Itti and Frédo Durand and Aude Oliva and Antonio Torralba and Matthias Bethge},
howpublished = {https://saliency.tuebingen.ai/},
title = {MIT/Tübingen Saliency Benchmark}
}
