THUS10000

by No License

THUS10000

The THUS10000 benchmark dataset comprises of 10,000 images, each of which has an unambiguous salient object and the object region is accurately annotated with pixel wise ground-truth labeling. We also provide saliency maps (170, 000 image) for our methods as well as other 15 state of the art methods. Saliency segmentation results for several state of the art methods are also available.References:Global Contrast based Salient Region Detection. Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xiaolei Huang, Shi-Min Hu. IEEE CVPR, 2011, p. 409-416.Salient Object Detection and Segmentation. Ming-Ming Cheng, Niloy J. Mitra, Xiaolei Huang, Philip H. S. Torr, Shi-Min Hu. Submitted to IEEE TPAMI (TPAMI-2011-10-0753), 2011.

Dataset Attributes

Label SVG
CategoriesSaliency, Object, Detection, Visual, Attention