Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376504480> ?p ?o ?g. }
- W4376504480 endingPage "2747" @default.
- W4376504480 startingPage "2736" @default.
- W4376504480 abstract "Abstract Objects in a real scene often occlude each other and inferring a complete appearance from the visible part is an important and challenging task. In this paper, the authors propose a self‐supervised generative adversarial network GIGAN (GAN for generating the invisible), which can generate the complete appearance of objects without labelled invisible part information. The authors build two cycle transformation networks CycleIncomplete (CycleI) and CycleComplete (CycleC) that share parameters to improve the accuracy of mask completion. This design does not require well‐matched training images and can make better use of the limited labelled samples. In addition, the authors propose a conditional normalization module and combine it with the inferred complete mask output. The combination not only enhances the content recovery ability and obtains more realistic outputs, but also improves the efficiency of the generation process. Experimental results show that compared with existing self‐supervised learning models, our method achieves l 1 error, mean intersection‐over‐union (mIOU), and Fréchet inception distance (FID) improvements on the COCOA and KINS datasets." @default.
- W4376504480 created "2023-05-15" @default.
- W4376504480 creator A5065548666 @default.
- W4376504480 creator A5090815103 @default.
- W4376504480 date "2023-05-12" @default.
- W4376504480 modified "2023-10-14" @default.
- W4376504480 title "GIGAN: Self‐supervised GAN for generating the invisible using cycle transformation and conditional normalization" @default.
- W4376504480 cites W1861492603 @default.
- W4376504480 cites W1998062602 @default.
- W4376504480 cites W2058943444 @default.
- W4376504480 cites W2086847993 @default.
- W4376504480 cites W2150066425 @default.
- W4376504480 cites W2168614750 @default.
- W4376504480 cites W2194775991 @default.
- W4376504480 cites W2317851288 @default.
- W4376504480 cites W2344939607 @default.
- W4376504480 cites W2412782625 @default.
- W4376504480 cites W2555182955 @default.
- W4376504480 cites W2558156561 @default.
- W4376504480 cites W2560023338 @default.
- W4376504480 cites W2604176797 @default.
- W4376504480 cites W2776638780 @default.
- W4376504480 cites W2804860796 @default.
- W4376504480 cites W2962793481 @default.
- W4376504480 cites W2963073614 @default.
- W4376504480 cites W2963108253 @default.
- W4376504480 cites W2963150697 @default.
- W4376504480 cites W2963167763 @default.
- W4376504480 cites W2963179609 @default.
- W4376504480 cites W2963243172 @default.
- W4376504480 cites W2963522749 @default.
- W4376504480 cites W2963585656 @default.
- W4376504480 cites W2963660453 @default.
- W4376504480 cites W2963800363 @default.
- W4376504480 cites W2963849369 @default.
- W4376504480 cites W2963857746 @default.
- W4376504480 cites W2964236837 @default.
- W4376504480 cites W2964309882 @default.
- W4376504480 cites W2964325922 @default.
- W4376504480 cites W2987322772 @default.
- W4376504480 cites W2990578105 @default.
- W4376504480 cites W2993182889 @default.
- W4376504480 cites W3000538487 @default.
- W4376504480 cites W3035637413 @default.
- W4376504480 cites W3047032303 @default.
- W4376504480 cites W3158248812 @default.
- W4376504480 cites W3169004342 @default.
- W4376504480 cites W3201721053 @default.
- W4376504480 cites W4239510810 @default.
- W4376504480 cites W4312495869 @default.
- W4376504480 cites W639708223 @default.
- W4376504480 doi "https://doi.org/10.1049/ipr2.12824" @default.
- W4376504480 hasPublicationYear "2023" @default.
- W4376504480 type Work @default.
- W4376504480 citedByCount "0" @default.
- W4376504480 crossrefType "journal-article" @default.
- W4376504480 hasAuthorship W4376504480A5065548666 @default.
- W4376504480 hasAuthorship W4376504480A5090815103 @default.
- W4376504480 hasBestOaLocation W43765044801 @default.
- W4376504480 hasConcept C104317684 @default.
- W4376504480 hasConcept C11413529 @default.
- W4376504480 hasConcept C119857082 @default.
- W4376504480 hasConcept C127413603 @default.
- W4376504480 hasConcept C136886441 @default.
- W4376504480 hasConcept C144024400 @default.
- W4376504480 hasConcept C146978453 @default.
- W4376504480 hasConcept C153180895 @default.
- W4376504480 hasConcept C154945302 @default.
- W4376504480 hasConcept C185592680 @default.
- W4376504480 hasConcept C19165224 @default.
- W4376504480 hasConcept C204241405 @default.
- W4376504480 hasConcept C39890363 @default.
- W4376504480 hasConcept C41008148 @default.
- W4376504480 hasConcept C55493867 @default.
- W4376504480 hasConcept C64543145 @default.
- W4376504480 hasConceptScore W4376504480C104317684 @default.
- W4376504480 hasConceptScore W4376504480C11413529 @default.
- W4376504480 hasConceptScore W4376504480C119857082 @default.
- W4376504480 hasConceptScore W4376504480C127413603 @default.
- W4376504480 hasConceptScore W4376504480C136886441 @default.
- W4376504480 hasConceptScore W4376504480C144024400 @default.
- W4376504480 hasConceptScore W4376504480C146978453 @default.
- W4376504480 hasConceptScore W4376504480C153180895 @default.
- W4376504480 hasConceptScore W4376504480C154945302 @default.
- W4376504480 hasConceptScore W4376504480C185592680 @default.
- W4376504480 hasConceptScore W4376504480C19165224 @default.
- W4376504480 hasConceptScore W4376504480C204241405 @default.
- W4376504480 hasConceptScore W4376504480C39890363 @default.
- W4376504480 hasConceptScore W4376504480C41008148 @default.
- W4376504480 hasConceptScore W4376504480C55493867 @default.
- W4376504480 hasConceptScore W4376504480C64543145 @default.
- W4376504480 hasIssue "9" @default.
- W4376504480 hasLocation W43765044801 @default.
- W4376504480 hasOpenAccess W4376504480 @default.
- W4376504480 hasPrimaryLocation W43765044801 @default.
- W4376504480 hasRelatedWork W1991269640 @default.
- W4376504480 hasRelatedWork W2016839265 @default.
- W4376504480 hasRelatedWork W2063185616 @default.