Title of Paper:Salient Object Detection via Multiple Instance Learning

Hits:

Date of Publication:2019-03-29

Journal:IEEE Transactions on Image Processing

Included Journals:SCI

Affiliation of Author(s):School of communication and information system

Key Words:Salient object

Abstract:Object proposals are a series of candidate segments
containing the objects of interest, which are taken as preprocessing
and widely applied in various vision tasks. However, most
of existing saliency approaches only utilizes the proposals to compute a location prior. In this paper, we naturally take the proposals as the bags of instances of multiple instances learning (MIL), where the instances are the superpixels contained in the proposals, and formulate saliency detection problem as an MIL task (i.e., predict the labels of instances using the classifier in the MIL framework). This method all