Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999455429> ?p ?o ?g. }
- W2999455429 abstract "We study the problem of learning to map, in an unsupervised way, between domains A and B, such that the samples b in B contain all the information that exists in samples a in A and some additional information. For example, ignoring occlusions, B can be people with glasses, A people without, and the glasses, would be the added information. When mapping a sample a from the first domain to the other domain, the missing information is replicated from an independent reference sample b in B. Thus, in the above example, we can create, for every person without glasses a version with the glasses observed in any face image. Our solution employs a single two-pathway encoder and a single decoder for both domains. The common part of the two domains and the separate part are encoded as two vectors, and the separate part is fixed at zero for domain A. The loss terms are minimal and involve reconstruction losses for the two domains and a domain confusion term. Our analysis shows that under mild assumptions, this architecture, which is much simpler than the literature guided-translation methods, is enough to ensure disentanglement between the two domains. We present convincing results in a few visual domains, such as no-glasses to glasses, adding facial hair based on a reference image, etc." @default.
- W2999455429 created "2020-01-23" @default.
- W2999455429 creator A5050776111 @default.
- W2999455429 creator A5058555772 @default.
- W2999455429 creator A5078102229 @default.
- W2999455429 creator A5081028371 @default.
- W2999455429 date "2020-01-14" @default.
- W2999455429 modified "2023-09-27" @default.
- W2999455429 title "Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer" @default.
- W2999455429 cites W135467536 @default.
- W2999455429 cites W1599814229 @default.
- W2999455429 cites W1617650991 @default.
- W2999455429 cites W1731081199 @default.
- W2999455429 cites W1959608418 @default.
- W2999455429 cites W1978380814 @default.
- W2999455429 cites W2045745231 @default.
- W2999455429 cites W2104094955 @default.
- W2999455429 cites W2131953535 @default.
- W2999455429 cites W2209882149 @default.
- W2999455429 cites W2434741482 @default.
- W2999455429 cites W2502312327 @default.
- W2999455429 cites W2622563070 @default.
- W2999455429 cites W2740132093 @default.
- W2999455429 cites W2760424551 @default.
- W2999455429 cites W2762484717 @default.
- W2999455429 cites W2768626898 @default.
- W2999455429 cites W2786772298 @default.
- W2999455429 cites W2787928077 @default.
- W2999455429 cites W2798600195 @default.
- W2999455429 cites W2799121188 @default.
- W2999455429 cites W2804532943 @default.
- W2999455429 cites W2807382363 @default.
- W2999455429 cites W2897699732 @default.
- W2999455429 cites W2902227449 @default.
- W2999455429 cites W2920544237 @default.
- W2999455429 cites W2949117887 @default.
- W2999455429 cites W2951939904 @default.
- W2999455429 cites W2962752582 @default.
- W2999455429 cites W2962793481 @default.
- W2999455429 cites W2962947361 @default.
- W2999455429 cites W2962964479 @default.
- W2999455429 cites W2963073614 @default.
- W2999455429 cites W2963330667 @default.
- W2999455429 cites W2963426391 @default.
- W2999455429 cites W2963444790 @default.
- W2999455429 cites W2963602293 @default.
- W2999455429 cites W2963784072 @default.
- W2999455429 cites W2964168187 @default.
- W2999455429 cites W2964341837 @default.
- W2999455429 cites W3159890710 @default.
- W2999455429 hasPublicationYear "2020" @default.
- W2999455429 type Work @default.
- W2999455429 sameAs 2999455429 @default.
- W2999455429 citedByCount "3" @default.
- W2999455429 countsByYear W29994554292020 @default.
- W2999455429 countsByYear W29994554292021 @default.
- W2999455429 crossrefType "posted-content" @default.
- W2999455429 hasAuthorship W2999455429A5050776111 @default.
- W2999455429 hasAuthorship W2999455429A5058555772 @default.
- W2999455429 hasAuthorship W2999455429A5078102229 @default.
- W2999455429 hasAuthorship W2999455429A5081028371 @default.
- W2999455429 hasConcept C101738243 @default.
- W2999455429 hasConcept C104317684 @default.
- W2999455429 hasConcept C105580179 @default.
- W2999455429 hasConcept C108583219 @default.
- W2999455429 hasConcept C11171543 @default.
- W2999455429 hasConcept C111919701 @default.
- W2999455429 hasConcept C115961682 @default.
- W2999455429 hasConcept C118505674 @default.
- W2999455429 hasConcept C134306372 @default.
- W2999455429 hasConcept C144024400 @default.
- W2999455429 hasConcept C149364088 @default.
- W2999455429 hasConcept C153180895 @default.
- W2999455429 hasConcept C154945302 @default.
- W2999455429 hasConcept C15744967 @default.
- W2999455429 hasConcept C185592680 @default.
- W2999455429 hasConcept C198531522 @default.
- W2999455429 hasConcept C2778152352 @default.
- W2999455429 hasConcept C2779304628 @default.
- W2999455429 hasConcept C2779757391 @default.
- W2999455429 hasConcept C2781140086 @default.
- W2999455429 hasConcept C33923547 @default.
- W2999455429 hasConcept C36289849 @default.
- W2999455429 hasConcept C36503486 @default.
- W2999455429 hasConcept C41008148 @default.
- W2999455429 hasConcept C43617362 @default.
- W2999455429 hasConcept C55493867 @default.
- W2999455429 hasConcept C8038995 @default.
- W2999455429 hasConceptScore W2999455429C101738243 @default.
- W2999455429 hasConceptScore W2999455429C104317684 @default.
- W2999455429 hasConceptScore W2999455429C105580179 @default.
- W2999455429 hasConceptScore W2999455429C108583219 @default.
- W2999455429 hasConceptScore W2999455429C11171543 @default.
- W2999455429 hasConceptScore W2999455429C111919701 @default.
- W2999455429 hasConceptScore W2999455429C115961682 @default.
- W2999455429 hasConceptScore W2999455429C118505674 @default.
- W2999455429 hasConceptScore W2999455429C134306372 @default.
- W2999455429 hasConceptScore W2999455429C144024400 @default.
- W2999455429 hasConceptScore W2999455429C149364088 @default.
- W2999455429 hasConceptScore W2999455429C153180895 @default.