GAPNET: GENERIC-ATTRIBUTE-POSE NETWORK FOR FINE-GRAINED VISUAL CATEGORIZATION USING MULTI-ATTRIBUTE ATTENTION MODULE

Cited 7 time in webofscience Cited 0 time in scopus
  • Hit : 79
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorJu, Minjeongko
dc.contributor.authorRyu, Hobinko
dc.contributor.authorMoon, Sangkeunko
dc.contributor.authorYoo, Chang-Dongko
dc.date.accessioned2021-10-27T08:30:23Z-
dc.date.available2021-10-27T08:30:23Z-
dc.date.created2021-10-19-
dc.date.created2021-10-19-
dc.date.issued2020-09-
dc.identifier.citationIEEE International Conference on Image Processing, ICIP 2020, pp.703 - 707-
dc.identifier.issn1522-4880-
dc.identifier.urihttp://hdl.handle.net/10203/288360-
dc.description.abstractThis paper proposes a multi-task learning framework for fine-grained visual categorization (FGVC) referred to as Generic-Attribute-Pose Network (GAPNet) that is capable of attending discriminating parts depending on the pose and part-attribute of an object using multi-attribute attention. FGVC is a challenging task that involves categorical data with small inter-class variation and large intra-class variation. Multi-Attribute Attention Module (MAAM) guides the GAPNet to focus on multiple parts of the image feature by emphasizing appropriate feature channels given both pose and part-attribute features. Experiments on Caltech-UCSD Birds and NABirds datasets demonstrate that GAPNet is competitive with other state-of-the-art methods, and ablation study on GAPNet conditioned on pose and part-attribute feature shows that GAPNet performs best when conditioned on both pose and part-attribute features.-
dc.languageEnglish-
dc.publisherIEEE-
dc.titleGAPNET: GENERIC-ATTRIBUTE-POSE NETWORK FOR FINE-GRAINED VISUAL CATEGORIZATION USING MULTI-ATTRIBUTE ATTENTION MODULE-
dc.typeConference-
dc.identifier.wosid000646178500140-
dc.identifier.scopusid2-s2.0-85098625582-
dc.type.rimsCONF-
dc.citation.beginningpage703-
dc.citation.endingpage707-
dc.citation.publicationnameIEEE International Conference on Image Processing, ICIP 2020-
dc.identifier.conferencecountryAR-
dc.identifier.conferencelocationVirtual-
dc.identifier.doi10.1109/ICIP40778.2020.9190875-
dc.contributor.localauthorYoo, Chang-Dong-
dc.contributor.nonIdAuthorJu, Minjeong-
dc.contributor.nonIdAuthorRyu, Hobin-
dc.contributor.nonIdAuthorMoon, Sangkeun-
Appears in Collection
EE-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 7 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0