Full metadata record
DC FieldValueLanguage
dc.contributor.authorHsu, Cheng-Chunen_US
dc.contributor.authorHsu, Kuang-Juien_US
dc.contributor.authorTsai, Chung-Chien_US
dc.contributor.authorLin, Yen-Yuen_US
dc.contributor.authorChuang, Yung-Yuen_US
dc.date.accessioned2020-07-01T05:21:49Z-
dc.date.available2020-07-01T05:21:49Z-
dc.date.issued2019-01-01en_US
dc.identifier.issn1049-5258en_US
dc.identifier.urihttp://hdl.handle.net/11536/154489-
dc.description.abstractThis paper presents a weakly supervised instance segmentation method that consumes training data with tight bounding box annotations. The major difficulty lies in the uncertain figure-ground separation within each bounding box since there is no supervisory signal about it. We address the difficulty by formulating the problem as a multiple instance learning (MIL) task, and generate positive and negative bags based on the sweeping lines of each bounding box. The proposed deep model integrates MIL into a fully supervised instance segmentation network, and can be derived by the objective consisting of two terms, i.e., the unary term and the pairwise term. The former estimates the foreground and background areas of each bounding box while the latter maintains the unity of the estimated object masks. The experimental results show that our method performs favorably against existing weakly supervised methods and even surpasses some fully supervised methods for instance segmentation on the PASCAL VOC dataset. The code is available at https://github.com/chengchunhsu/WSIS_BBTP.en_US
dc.language.isoen_USen_US
dc.titleWeakly Supervised Instance Segmentation using the Bounding Box Tightness Prioren_US
dc.typeProceedings Paperen_US
dc.identifier.journalADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019)en_US
dc.citation.volume32en_US
dc.citation.spage0en_US
dc.citation.epage0en_US
dc.contributor.department交大名義發表zh_TW
dc.contributor.departmentNational Chiao Tung Universityen_US
dc.identifier.wosnumberWOS:000534424306057en_US
dc.citation.woscount0en_US
Appears in Collections:Conferences Paper