Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/139895
Title: Salient Object Detection via Multiple Instance Learning
Authors: Fang Huang;Jinqing Qi;Huchuan Lu;Lihe Zhang;Xiang Ruan
Year: 2017
Publisher: IEEE
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 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 state-of-art saliency detection methods on several benchmark data sets.
URI: http://localhost/handle/Hannan/139895
volume: 26
issue: 4
More Information: 1911,
1922
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7857049.pdf3.05 MBAdobe PDF
Title: Salient Object Detection via Multiple Instance Learning
Authors: Fang Huang;Jinqing Qi;Huchuan Lu;Lihe Zhang;Xiang Ruan
Year: 2017
Publisher: IEEE
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 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 state-of-art saliency detection methods on several benchmark data sets.
URI: http://localhost/handle/Hannan/139895
volume: 26
issue: 4
More Information: 1911,
1922
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7857049.pdf3.05 MBAdobe PDF
Title: Salient Object Detection via Multiple Instance Learning
Authors: Fang Huang;Jinqing Qi;Huchuan Lu;Lihe Zhang;Xiang Ruan
Year: 2017
Publisher: IEEE
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 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 state-of-art saliency detection methods on several benchmark data sets.
URI: http://localhost/handle/Hannan/139895
volume: 26
issue: 4
More Information: 1911,
1922
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7857049.pdf3.05 MBAdobe PDF