Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288364045> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4288364045 abstract "Unpaired Image-to-Image Translation (UIT) focuses on translating images among different domains by using unpaired data, which has received increasing research focus due to its practical usage. However, existing UIT schemes defect in the need of supervised training, as well as the lack of encoding domain information. In this paper, we propose an Attribute Guided UIT model termed AGUIT to tackle these two challenges. AGUIT considers multi-modal and multi-domain tasks of UIT jointly with a novel semi-supervised setting, which also merits in representation disentanglement and fine control of outputs. Especially, AGUIT benefits from two-fold: (1) It adopts a novel semi-supervised learning process by translating attributes of labeled data to unlabeled data, and then reconstructing the unlabeled data by a cycle consistency operation. (2) It decomposes image representation into domain-invariant content code and domain-specific style code. The redesigned style code embeds image style into two variables drawn from standard Gaussian distribution and the distribution of domain label, which facilitates the fine control of translation due to the continuity of both variables. Finally, we introduce a new challenge, i.e., disentangled transfer, for UIT models, which adopts the disentangled representation to translate data less related with the training set. Extensive experiments demonstrate the capacity of AGUIT over existing state-of-the-art models." @default.
- W4288364045 created "2022-07-29" @default.
- W4288364045 creator A5015317495 @default.
- W4288364045 creator A5016080094 @default.
- W4288364045 creator A5016926371 @default.
- W4288364045 creator A5017979697 @default.
- W4288364045 creator A5034631079 @default.
- W4288364045 creator A5037921837 @default.
- W4288364045 creator A5089218234 @default.
- W4288364045 date "2019-04-28" @default.
- W4288364045 modified "2023-10-14" @default.
- W4288364045 title "Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning" @default.
- W4288364045 doi "https://doi.org/10.48550/arxiv.1904.12428" @default.
- W4288364045 hasPublicationYear "2019" @default.
- W4288364045 type Work @default.
- W4288364045 citedByCount "0" @default.
- W4288364045 crossrefType "posted-content" @default.
- W4288364045 hasAuthorship W4288364045A5015317495 @default.
- W4288364045 hasAuthorship W4288364045A5016080094 @default.
- W4288364045 hasAuthorship W4288364045A5016926371 @default.
- W4288364045 hasAuthorship W4288364045A5017979697 @default.
- W4288364045 hasAuthorship W4288364045A5034631079 @default.
- W4288364045 hasAuthorship W4288364045A5037921837 @default.
- W4288364045 hasAuthorship W4288364045A5089218234 @default.
- W4288364045 hasBestOaLocation W42883640451 @default.
- W4288364045 hasConcept C115961682 @default.
- W4288364045 hasConcept C116409475 @default.
- W4288364045 hasConcept C119857082 @default.
- W4288364045 hasConcept C134306372 @default.
- W4288364045 hasConcept C153180895 @default.
- W4288364045 hasConcept C154945302 @default.
- W4288364045 hasConcept C177264268 @default.
- W4288364045 hasConcept C17744445 @default.
- W4288364045 hasConcept C199360897 @default.
- W4288364045 hasConcept C199539241 @default.
- W4288364045 hasConcept C204321447 @default.
- W4288364045 hasConcept C2776359362 @default.
- W4288364045 hasConcept C2776434776 @default.
- W4288364045 hasConcept C2776436953 @default.
- W4288364045 hasConcept C2776760102 @default.
- W4288364045 hasConcept C2779757391 @default.
- W4288364045 hasConcept C33923547 @default.
- W4288364045 hasConcept C36503486 @default.
- W4288364045 hasConcept C41008148 @default.
- W4288364045 hasConcept C94625758 @default.
- W4288364045 hasConcept C95623464 @default.
- W4288364045 hasConceptScore W4288364045C115961682 @default.
- W4288364045 hasConceptScore W4288364045C116409475 @default.
- W4288364045 hasConceptScore W4288364045C119857082 @default.
- W4288364045 hasConceptScore W4288364045C134306372 @default.
- W4288364045 hasConceptScore W4288364045C153180895 @default.
- W4288364045 hasConceptScore W4288364045C154945302 @default.
- W4288364045 hasConceptScore W4288364045C177264268 @default.
- W4288364045 hasConceptScore W4288364045C17744445 @default.
- W4288364045 hasConceptScore W4288364045C199360897 @default.
- W4288364045 hasConceptScore W4288364045C199539241 @default.
- W4288364045 hasConceptScore W4288364045C204321447 @default.
- W4288364045 hasConceptScore W4288364045C2776359362 @default.
- W4288364045 hasConceptScore W4288364045C2776434776 @default.
- W4288364045 hasConceptScore W4288364045C2776436953 @default.
- W4288364045 hasConceptScore W4288364045C2776760102 @default.
- W4288364045 hasConceptScore W4288364045C2779757391 @default.
- W4288364045 hasConceptScore W4288364045C33923547 @default.
- W4288364045 hasConceptScore W4288364045C36503486 @default.
- W4288364045 hasConceptScore W4288364045C41008148 @default.
- W4288364045 hasConceptScore W4288364045C94625758 @default.
- W4288364045 hasConceptScore W4288364045C95623464 @default.
- W4288364045 hasLocation W42883640451 @default.
- W4288364045 hasOpenAccess W4288364045 @default.
- W4288364045 hasPrimaryLocation W42883640451 @default.
- W4288364045 hasRelatedWork W2772222351 @default.
- W4288364045 hasRelatedWork W2890993870 @default.
- W4288364045 hasRelatedWork W2963403405 @default.
- W4288364045 hasRelatedWork W2983825237 @default.
- W4288364045 hasRelatedWork W2995469692 @default.
- W4288364045 hasRelatedWork W3093339210 @default.
- W4288364045 hasRelatedWork W3198510459 @default.
- W4288364045 hasRelatedWork W3208067003 @default.
- W4288364045 hasRelatedWork W3213366174 @default.
- W4288364045 hasRelatedWork W4287997295 @default.
- W4288364045 isParatext "false" @default.
- W4288364045 isRetracted "false" @default.
- W4288364045 workType "article" @default.