Show simple item record

dc.contributor.authorZhang, Yongqiang
dc.contributor.authorDing, Mingli
dc.contributor.authorBai, Yancheng
dc.contributor.authorXu, Mengmeng
dc.contributor.authorGhanem, Bernard
dc.date.accessioned2019-07-04T12:22:12Z
dc.date.available2019-07-04T12:22:12Z
dc.date.issued2019-02-11
dc.identifier.citationZhang, Y., Ding, M., Bai, Y., Xu, M., & Ghanem, B. (2020). Beyond Weakly Supervised: Pseudo Ground Truths Mining for Missing Bounding-Boxes Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 30(4), 983–997. doi:10.1109/tcsvt.2019.2898559
dc.identifier.doi10.1109/TCSVT.2019.2898559
dc.identifier.urihttp://hdl.handle.net/10754/655921
dc.description.abstractDue to the shortcomings of the weakly-supervised and fully-supervised object detection (i.e. unsatisfactory performance and expensive annotations, respectively), leveraging partially labeled images in a cost-effective way to train an object detector has attracted much attention. In this paper, we formulate this challenging task as a missing bounding-boxes object detection problem. Specifically, we develop a pseudo ground truth mining (PGTM) procedure to automatically find the missing bounding-boxes for the unlabeled instances, called pseudo ground truths here, in the training data, and then combine the mined pseudo ground truths and the labeled annotations to train a fully-supervised object detector. Furthermore, we further propose an incremental learning (IL) framework to gradually incorporate the results of the trained fully-supervised detector to improve the performance of missing bounding-boxes object detection. More importantly, we find an effective way to label the massive images with limited labors and funds, which is crucial when building a large-scale weakly/webly labeled dataset for object detection. Extensive experiments on the PASCAL VOC and COCO benchmarks demonstrate that our proposed method can narrow the gap between fully-supervised and weakly-supervised object detectors, and we outperform the previous state-of-the-art weakly-supervised detectors by a large margin (more than 3% mAP absolutely) when the missing rate equals 0.9. Moreover, our proposed method with 30% missing bounding-box annotations can achieve comparable performance to some fully-supervised detectors.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/8638807/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8638807
dc.rights(c) 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
dc.subjectPseudo ground truths
dc.subjectweakly/semi-supervised
dc.subjectobject detection
dc.subjectmissing bounding-boxes
dc.titleBeyond Weakly-supervised: Pseudo Ground Truths Mining for Missing Bounding-boxes Object Detection
dc.typeArticle
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentVisual Computing Center
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journalIEEE Transactions on Circuits and Systems for Video Technology
dc.eprint.versionPost-print
dc.contributor.institutionSchool of Electrical Engineering and Automation, Harbin Institute of Technology (HIT), Harbin, China.
kaust.personBai, Yancheng
kaust.personXu, Mengmeng
kaust.personGhanem, Bernard
refterms.dateFOA2019-07-04T12:23:36Z
dc.date.published-online2019-02-11
dc.date.published-print2020-04


Files in this item

Thumbnail
Name:
08638807.pdf
Size:
2.813Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record