Matches in SemOpenAlex for { <https://semopenalex.org/work/W2610366607> ?p ?o ?g. }
- W2610366607 abstract "Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains non-trivial. Not only is the number of possible comparisons quadratic in the number of training images, but also access to images adequately spanning the space of fine-grained visual differences is limited. We propose to overcome the sparsity of supervision problem via synthetically generated images. Building on a state-of-the-art image generation engine, we sample pairs of training images exhibiting slight modifications of individual attributes. Augmenting real training image pairs with these examples, we then train attribute ranking models to predict the relative strength of an attribute in novel pairs of real images. Our results on datasets of faces and fashion images show the great promise of bootstrapping imperfect image generators to counteract sample sparsity for learning to rank." @default.
- W2610366607 created "2017-05-12" @default.
- W2610366607 creator A5012765543 @default.
- W2610366607 creator A5035740091 @default.
- W2610366607 date "2017-10-01" @default.
- W2610366607 modified "2023-10-13" @default.
- W2610366607 title "Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images" @default.
- W2610366607 cites W1893585201 @default.
- W2610366607 cites W1950149599 @default.
- W2610366607 cites W1965814436 @default.
- W2610366607 cites W1978370894 @default.
- W2610366607 cites W1981219830 @default.
- W2610366607 cites W2010239981 @default.
- W2610366607 cites W2025768430 @default.
- W2610366607 cites W2037560589 @default.
- W2610366607 cites W2047221353 @default.
- W2610366607 cites W2050818842 @default.
- W2610366607 cites W2056763477 @default.
- W2610366607 cites W2083366168 @default.
- W2610366607 cites W2093848332 @default.
- W2610366607 cites W2112053844 @default.
- W2610366607 cites W2112055291 @default.
- W2610366607 cites W2119713953 @default.
- W2610366607 cites W2143331230 @default.
- W2610366607 cites W2144796873 @default.
- W2610366607 cites W2152926413 @default.
- W2610366607 cites W2156163116 @default.
- W2610366607 cites W2163078148 @default.
- W2610366607 cites W2166761907 @default.
- W2610366607 cites W2172156083 @default.
- W2610366607 cites W2200019946 @default.
- W2610366607 cites W2221516161 @default.
- W2610366607 cites W2294130536 @default.
- W2610366607 cites W2429267751 @default.
- W2610366607 cites W2467570466 @default.
- W2610366607 cites W2499554887 @default.
- W2610366607 cites W2536626143 @default.
- W2610366607 cites W2962759496 @default.
- W2610366607 cites W2963567641 @default.
- W2610366607 cites W4210969899 @default.
- W2610366607 cites W88868203 @default.
- W2610366607 cites W2137585067 @default.
- W2610366607 doi "https://doi.org/10.1109/iccv.2017.594" @default.
- W2610366607 hasPublicationYear "2017" @default.
- W2610366607 type Work @default.
- W2610366607 sameAs 2610366607 @default.
- W2610366607 citedByCount "77" @default.
- W2610366607 countsByYear W26103666072018 @default.
- W2610366607 countsByYear W26103666072019 @default.
- W2610366607 countsByYear W26103666072020 @default.
- W2610366607 countsByYear W26103666072021 @default.
- W2610366607 countsByYear W26103666072022 @default.
- W2610366607 countsByYear W26103666072023 @default.
- W2610366607 crossrefType "proceedings-article" @default.
- W2610366607 hasAuthorship W2610366607A5012765543 @default.
- W2610366607 hasAuthorship W2610366607A5035740091 @default.
- W2610366607 hasBestOaLocation W26103666072 @default.
- W2610366607 hasConcept C114614502 @default.
- W2610366607 hasConcept C115961682 @default.
- W2610366607 hasConcept C119857082 @default.
- W2610366607 hasConcept C149782125 @default.
- W2610366607 hasConcept C153180895 @default.
- W2610366607 hasConcept C154945302 @default.
- W2610366607 hasConcept C164226766 @default.
- W2610366607 hasConcept C185592680 @default.
- W2610366607 hasConcept C189430467 @default.
- W2610366607 hasConcept C198531522 @default.
- W2610366607 hasConcept C207609745 @default.
- W2610366607 hasConcept C31972630 @default.
- W2610366607 hasConcept C33923547 @default.
- W2610366607 hasConcept C41008148 @default.
- W2610366607 hasConcept C43617362 @default.
- W2610366607 hasConcept C86037889 @default.
- W2610366607 hasConceptScore W2610366607C114614502 @default.
- W2610366607 hasConceptScore W2610366607C115961682 @default.
- W2610366607 hasConceptScore W2610366607C119857082 @default.
- W2610366607 hasConceptScore W2610366607C149782125 @default.
- W2610366607 hasConceptScore W2610366607C153180895 @default.
- W2610366607 hasConceptScore W2610366607C154945302 @default.
- W2610366607 hasConceptScore W2610366607C164226766 @default.
- W2610366607 hasConceptScore W2610366607C185592680 @default.
- W2610366607 hasConceptScore W2610366607C189430467 @default.
- W2610366607 hasConceptScore W2610366607C198531522 @default.
- W2610366607 hasConceptScore W2610366607C207609745 @default.
- W2610366607 hasConceptScore W2610366607C31972630 @default.
- W2610366607 hasConceptScore W2610366607C33923547 @default.
- W2610366607 hasConceptScore W2610366607C41008148 @default.
- W2610366607 hasConceptScore W2610366607C43617362 @default.
- W2610366607 hasConceptScore W2610366607C86037889 @default.
- W2610366607 hasLocation W26103666071 @default.
- W2610366607 hasLocation W26103666072 @default.
- W2610366607 hasOpenAccess W2610366607 @default.
- W2610366607 hasPrimaryLocation W26103666071 @default.
- W2610366607 hasRelatedWork W1786507113 @default.
- W2610366607 hasRelatedWork W2293317945 @default.
- W2610366607 hasRelatedWork W2499321295 @default.
- W2610366607 hasRelatedWork W2572749905 @default.
- W2610366607 hasRelatedWork W2950017439 @default.
- W2610366607 hasRelatedWork W2963493716 @default.
- W2610366607 hasRelatedWork W3127142483 @default.