ImgSal McGill Database for Saliency Detection

Author: McGill University

Partner: No

Contact: Jian Li (




Total: 235

Ratings: 21


Existing saliency benchmarks (e.g. Bruce’s dataset, Hou’dataset, Harel’s dataset and so on) are collections of images, with no attempt to categorize the difficulty of analysis required. Hence, ImgSal presents new saliency benchmark for saliency models validation. The database provide both REGION ground truth (human labeled) and FIXATION ground truth (by eye tracker). ImgSal features: (1) Collection of 235 color images, which are divided into six different categorie, (2) Provide both human fixation records (saccades data) and human labeled results, (3) Easy to use. ROC and PoDSC evaluation codes.


Various data files can be downloaded from the website. Link:

Broken link!

The original link was: