Instance annotation via optimal BoW for weakly supervised object localization

Wang, Liantao, Meng, Deyu, Hu, Xuelei, Lu, Jianfeng and Zhao, Ji (2017) Instance annotation via optimal BoW for weakly supervised object localization. IEEE Transactions on Cybernetics, 47 5: 1313-1324. doi:10.1109/TCYB.2017.2647965


Author Wang, Liantao
Meng, Deyu
Hu, Xuelei
Lu, Jianfeng
Zhao, Ji
Title Instance annotation via optimal BoW for weakly supervised object localization
Journal name IEEE Transactions on Cybernetics   Check publisher's open access policy
ISSN 2168-2267
2168-2275
Publication date 2017-05-01
Sub-type Article (original research)
DOI 10.1109/TCYB.2017.2647965
Open Access Status Not yet assessed
Volume 47
Issue 5
Start page 1313
End page 1324
Total pages 12
Place of publication Piscataway, NJ, United States
Publisher Institute of Electrical and Electronics Engineers
Language eng
Abstract In this paper, we aim at irregular-shape object localization under weak supervision. With over-segmentation, this task can be transformed into multiple-instance context. However, most multiple-instance learning methods only emphasize single most positive instance in a positive bag to optimize bag-level classification, and leads to imprecise or incomplete localization. To address this issue, we propose a scheme for instance annotation, where all of the positive instances are detected by labeling each instance in each positive bag. Inspired by the successful application of bag-of-words (BoW) to feature representation, we leverage it at instance-level to model the distributions of the positive class and negative class, and then incorporate the BoW learning and instance labeling in a single optimization formulation. We also demonstrate that the scheme is well suited to weakly supervised object localization of irregular-shape. Experimental results validate the effectiveness both for the problem of generic instance annotation and for the application of weakly supervised object localization compared to some existing methods.
Keyword Bag-of-words (BoWs)
Instance annotation
Object localization
Weakly supervised learning
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: HERDC Pre-Audit
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 09 May 2017, 00:23:47 EST by System User on behalf of Learning and Research Services (UQ Library)