Saliency from High-Level Semantic Image Features

Aymen Azaza, Joost van de Weijer, Ali Douik, Javad Zolfaghari Bengar, Marc Masana Castrillo

Research output: Contribution to journalArticlepeer-review


Top-down semantic information is known to play an important role in assigning saliency. Recently, large strides have been made in improving state-of-the-art semantic image understanding in the felds of object detection and semantic segmentation. Therefore, since these methods have now reached a high-level of maturity, evaluation of the impact of high-level image understanding on saliency estimation is now feasible. We propose several saliency features which are computed from object detection and semantic segmentation results. We combine these features with a standard baseline method for saliency detection to evaluate their importance. Experiments demonstrate that the proposed features derived from object detection and semantic segmentation improve saliency estimation signifcantly. Moreover, they show that our method obtains state-of-theart results on (FT, ImgSal, and SOD datasets) and obtains competitive results on four other datasets (ECSSD, PASCAL-S, MSRA-B, and HKU-IS).
Original languageEnglish
JournalSN Computer Science
Publication statusPublished - Jul 2020


Dive into the research topics of 'Saliency from High-Level Semantic Image Features'. Together they form a unique fingerprint.

Cite this