Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network

Cited 97 time in webofscience Cited 126 time in scopus
  • Hit : 215
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorHong, Seunghoonko
dc.contributor.authorOh, Junhyukko
dc.contributor.authorLee, Honglakko
dc.contributor.authorHan, Bohyungko
dc.date.accessioned2019-12-13T13:26:30Z-
dc.date.available2019-12-13T13:26:30Z-
dc.date.created2019-11-05-
dc.date.created2019-11-05-
dc.date.issued2016-06-26-
dc.identifier.citation29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, pp.3204 - 3212-
dc.identifier.urihttp://hdl.handle.net/10203/269639-
dc.description.abstractWe propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised approaches, our algorithm exploits auxiliary segmentation annotations available for different categories to guide segmentations on images with only image-level class labels. To make segmentation knowledge transferrable across categories, we design a decoupled encoder-decoder architecture with attention model. In this architecture, the model generates spatial highlights of each category presented in images using an attention model, and subsequently performs binary segmentation for each highlighted region using decoder. Combining attention model, the decoder trained with segmentation annotations in different categories boosts accuracy of weakly-supervised semantic segmentation. The proposed algorithm demonstrates substantially improved performance compared to the state-of-theart weakly-supervised techniques in PASCAL VOC 2012 dataset when our model is trained with the annotations in 60 exclusive categories in Microsoft COCO dataset.-
dc.languageEnglish-
dc.publisherIEEE Computer Society and the Computer Vision Foundation (CVF)-
dc.titleLearning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network-
dc.typeConference-
dc.identifier.wosid000400012303029-
dc.identifier.scopusid2-s2.0-84986274543-
dc.type.rimsCONF-
dc.citation.beginningpage3204-
dc.citation.endingpage3212-
dc.citation.publicationname29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationCaesars Palace, Las Vegas-
dc.identifier.doi10.1109/CVPR.2016.349-
dc.contributor.localauthorHong, Seunghoon-
dc.contributor.nonIdAuthorOh, Junhyuk-
dc.contributor.nonIdAuthorLee, Honglak-
dc.contributor.nonIdAuthorHan, Bohyung-
Appears in Collection
CS-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 97 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0