Co-bootstrapping saliency

Huchuan Lu, Xiaoning Zhang, Jinqing Qi, Na Tong, Xiang Ruan, Ming Hsuan Yang

Research output: Contribution to journalArticlepeer-review

30 Citations (Scopus)


In this paper, we propose a visual saliency detection algorithm to explore the fusion of various saliency models in a manner of bootstrap learning. First, an original bootstrapping model, which combines both weak and strong saliency models, is constructed. In this model, image priors are exploited to generate an original weak saliency model, which provides training samples for a strong model. Then, a strong classifier is learned based on the samples extracted from the weak model. We use this classifier to classify all the salient and non-salient superpixels in an input image. To further improve the detection performance, multi-scale saliency maps of weak and strong model are integrated, respectively. The final result is the combination of the weak and strong saliency maps. The original model indicates that the overall performance of the proposed algorithm is largely affected by the quality of weak saliency model. Therefore, we propose a co-bootstrapping mechanism, which integrates the advantages of different saliency methods to construct the weak saliency model thus addresses the problem and achieves a better performance. Extensive experiments on benchmark data sets demonstrate that the proposed algorithm outperforms the state-of-the-art methods.

Original languageEnglish
Article number7742419
Pages (from-to)414-425
Number of pages12
JournalIEEE Transactions on Image Processing
Issue number1
Publication statusPublished - 2017 Jan

Bibliographical note

Funding Information:
This work was supported by the National Natural Science Foundation of China under Grant 61528101 and Grant 61472060.

Publisher Copyright:
© 1992-2012 IEEE.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Co-bootstrapping saliency'. Together they form a unique fingerprint.

Cite this