Image datasets used for salient objects?

Question

I would like to understand reasons for different image datasets used for salient object detection: their difficulties, their origins and likely future datasets. Does there exist any work explaining them such their progression and characteristics over time?

Answer 1

Datasets explicitly mentioning saliency

1. MSRA
2. SOD based on BSD Berkeley segmentation dataset

Apparently more general datasets (not researched in detail)

3. DUT-Omron Image dataset
4. THUS
5. ECSD
6. PASCAL
7. ...

More challenging situations with more noise

• Detection on magnetism such as MR: Medical image dataset and Extract voice from magnetic tape