Weakly supervised object localization with multi-fold multiple instance learning

Simple item page
dc.citation.epage203en_US
dc.citation.issueNumber1en_US
dc.citation.spage189en_US
dc.citation.volumeNumber39en_US
dc.contributor.authorCinbis, R. G.en_US
dc.contributor.authorVerbeek, J.en_US
dc.contributor.authorSchmid, C.en_US
dc.date.accessioned2018-04-12T11:02:50Z
dc.date.available2018-04-12T11:02:50Z
dc.date.issued2017en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractObject category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. This procedure is particularly important when using high-dimensional representations, such as Fisher vectors and convolutional neural network features. We also propose a window refinement method, which improves the localization accuracy by incorporating an objectness prior. We present a detailed experimental evaluation using the PASCAL VOC 2007 dataset, which verifies the effectiveness of our approach. © 2016 IEEE.en_US
dc.identifier.doi10.1109/TPAMI.2016.2535231en_US
dc.identifier.issn0162-8828
dc.identifier.urihttp://hdl.handle.net/11693/37100
dc.language.isoEnglishen_US
dc.publisherIEEE Computer Societyen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/TPAMI.2016.2535231en_US
dc.source.titleIEEE Transactions on Pattern Analysis and Machine Intelligenceen_US
dc.subjectObject detectionen_US
dc.subjectWeakly supervised learningen_US
dc.subjectComputer visionen_US
dc.subjectIterative methodsen_US
dc.subjectLearning systemsen_US
dc.subjectLocationen_US
dc.subjectLocks (fasteners)en_US
dc.subjectNeural networksen_US
dc.subjectSupervised learningen_US
dc.subjectConvolutional neural networken_US
dc.subjectExperimental evaluationen_US
dc.subjectLocalization accuracyen_US
dc.subjectMultiple instance learningen_US
dc.subjectObject localizationen_US
dc.subjectRefinement methodsen_US
dc.subjectSupervised trainingsen_US
dc.subjectObject recognitionen_US
dc.titleWeakly supervised object localization with multi-fold multiple instance learningen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Weakly Supervised Object Localization.pdf
Size:
1.2 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download
Collections
Department of Computer Engineering