Bagging-based saliency distribution learning for visual saliency detection

作者：

Highlights：

• We propose a novel bagging-based saliency distribution learning framework for visual saliency detection.

• We propose a so called foreground consistency saliency optimization framework to further refine saliency map.

• An effective prejudgment mechanism is developed to improve computational efficiency.

• Experimental results on four datasets indicate the effectiveness of the proposed method.

摘要

•We propose a novel bagging-based saliency distribution learning framework for visual saliency detection.•We propose a so called foreground consistency saliency optimization framework to further refine saliency map.•An effective prejudgment mechanism is developed to improve computational efficiency.•Experimental results on four datasets indicate the effectiveness of the proposed method.

论文关键词：Saliency detection,Prior knowledge,Bagging method,Saliency distribution learning,Saliency optimization,Prejudgment mechanism

论文评审过程：Received 14 August 2019, Revised 22 March 2020, Accepted 21 June 2020, Available online 25 June 2020, Version of Record 27 June 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115928