点击次数：

论文类型：期刊论文

发表时间：2017-04-01

发表刊物：IEEE TRANSACTIONS ON IMAGE PROCESSING

收录刊物：SCIE、EI

卷号：26

期号：4

页面范围：1911-1922

ISSN号：1057-7149

关键字：Saliency detection; multiple instance learning; object proposal; optimization mechanism

摘要：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 allows some flexibility in finding a decision boundary based on the bag-level representations and can identify salient superpixels from ambiguous proposals. In addition, we introduce the MIL to an optimization mechanism, which iteratively updates training bags from easy to complex ones to learn a strong model. The significant improvement can be consistently achieved when applying the optimization model to existing saliency approaches. Extensive experiments demonstrate that the proposed algorithms perform favorably against the stateof- art saliency detection methods on several benchmark data sets.