Salient Object Detection via Multiple Instance Learning

Object proposals are a series of candidate segments containing objects of interest, which are taken as preprocessing and widely applied in various vision tasks. However, most of existing saliency approaches only utilize the proposals to compute a location prior. In this paper, we naturally take the...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 26(2017), 4 vom: 16. Apr., Seite 1911-1922
1. Verfasser: Huang, Fang (VerfasserIn)
Weitere Verfasser: Jinqing, Qi, Lu, Huchuan, Zhang, Lihe, Ruan, Xiang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2017
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM269066403
003 DE-627
005 20231224223837.0
007 cr uuu---uuuuu
008 231224s2017 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2017.2669878  |2 doi 
028 5 2 |a pubmed24n0896.xml 
035 |a (DE-627)NLM269066403 
035 |a (NLM)28212086 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Huang, Fang  |e verfasserin  |4 aut 
245 1 0 |a Salient Object Detection via Multiple Instance Learning 
264 1 |c 2017 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 20.11.2019 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Object proposals are a series of candidate segments containing objects of interest, which are taken as preprocessing and widely applied in various vision tasks. However, most of existing saliency approaches only utilize the proposals to compute a location prior. In this paper, we naturally take the proposals as the bags of instances of multiple instance learning (MIL), where the instances are the superpixels contained in the proposals, and formulate saliency detection problem as a 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 datasets 
650 4 |a Journal Article 
700 1 |a Jinqing, Qi  |e verfasserin  |4 aut 
700 1 |a Lu, Huchuan  |e verfasserin  |4 aut 
700 1 |a Zhang, Lihe  |e verfasserin  |4 aut 
700 1 |a Ruan, Xiang  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 26(2017), 4 vom: 16. Apr., Seite 1911-1922  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:26  |g year:2017  |g number:4  |g day:16  |g month:04  |g pages:1911-1922 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2017.2669878  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 26  |j 2017  |e 4  |b 16  |c 04  |h 1911-1922