Correspondence Driven Saliency Transfer

Wenguan Wang, Jianbing Shen, Ling Shao, Fatih Porikli

Research output: Contribution to journalArticlepeer-review

131 Citations (Scopus)


In this paper, we show that large annotated data sets have great potential to provide strong priors for saliency estimation rather than merely serving for benchmark evaluations. To this end, we present a novel image saliency detection method called saliency transfer. Given an input image, we first retrieve a support set of best matches from the large database of saliency annotated images. Then, we assign the transitional saliency scores by warping the support set annotations onto the input image according to computed dense correspondences. To incorporate context, we employ two complementary correspondence strategies: a global matching scheme based on scene-level analysis and a local matching scheme based on patch-level inference. We then introduce two refinement measures to further refine the saliency maps and apply the random-walk-with-restart by exploring the global saliency structure to estimate the affinity between foreground and background assignments. Extensive experimental results on four publicly available benchmark data sets demonstrate that the proposed saliency algorithm consistently outperforms the current state-of-the-art methods.
Original languageEnglish
Pages (from-to)5025-5034
JournalIEEE Transactions on Image Processing
Issue number11
Early online date19 Aug 2016
Publication statusPublished - Nov 2016


Dive into the research topics of 'Correspondence Driven Saliency Transfer'. Together they form a unique fingerprint.

Cite this