Matches in SemOpenAlex for { <https://semopenalex.org/work/W2920684403> ?p ?o ?g. }
- W2920684403 abstract "Deep generative models are becoming a cornerstone of modern machine learning. Recent work on conditional generative adversarial networks has shown that learning complex, high-dimensional distributions over natural images is within reach. While the latest models are able to generate high-fidelity, diverse natural images at high resolution, they rely on a vast quantity of labeled data. In this work we demonstrate how one can benefit from recent work on self- and semi-supervised learning to outperform the state of the art on both unsupervised ImageNet synthesis, as well as in the conditional setting. In particular, the proposed approach is able to match the sample quality (as measured by FID) of the current state-of-the-art conditional model BigGAN on ImageNet using only 10% of the labels and outperform it using 20% of the labels." @default.
- W2920684403 created "2019-03-11" @default.
- W2920684403 creator A5041958651 @default.
- W2920684403 creator A5044677020 @default.
- W2920684403 creator A5068127101 @default.
- W2920684403 creator A5071668416 @default.
- W2920684403 creator A5088082340 @default.
- W2920684403 creator A5089890773 @default.
- W2920684403 date "2019-03-06" @default.
- W2920684403 modified "2023-09-27" @default.
- W2920684403 title "High-Fidelity Image Generation With Fewer Labels" @default.
- W2920684403 cites W1520997877 @default.
- W2920684403 cites W2099471712 @default.
- W2920684403 cites W2142838865 @default.
- W2920684403 cites W2201912979 @default.
- W2920684403 cites W2267126114 @default.
- W2920684403 cites W2321533354 @default.
- W2920684403 cites W2412510955 @default.
- W2920684403 cites W2545656684 @default.
- W2920684403 cites W2548275288 @default.
- W2920684403 cites W2622263826 @default.
- W2920684403 cites W2749812777 @default.
- W2920684403 cites W2782980316 @default.
- W2920684403 cites W2804078698 @default.
- W2920684403 cites W2805984778 @default.
- W2920684403 cites W2843598537 @default.
- W2920684403 cites W2883725317 @default.
- W2920684403 cites W2893749619 @default.
- W2920684403 cites W2899508538 @default.
- W2920684403 cites W2902630600 @default.
- W2920684403 cites W2913939497 @default.
- W2920684403 cites W2949382160 @default.
- W2920684403 cites W2953327099 @default.
- W2920684403 cites W2962695743 @default.
- W2920684403 cites W2962742544 @default.
- W2920684403 cites W2962754210 @default.
- W2920684403 cites W2962770929 @default.
- W2920684403 cites W2963113011 @default.
- W2920684403 cites W2963245493 @default.
- W2920684403 cites W2963250052 @default.
- W2920684403 cites W2963373786 @default.
- W2920684403 cites W2963474063 @default.
- W2920684403 cites W2963629403 @default.
- W2920684403 cites W2963711386 @default.
- W2920684403 cites W2963836885 @default.
- W2920684403 cites W2963873275 @default.
- W2920684403 cites W2963981733 @default.
- W2920684403 cites W2964037671 @default.
- W2920684403 cites W2964137095 @default.
- W2920684403 cites W2964218010 @default.
- W2920684403 cites W2964316369 @default.
- W2920684403 cites W343636949 @default.
- W2920684403 hasPublicationYear "2019" @default.
- W2920684403 type Work @default.
- W2920684403 sameAs 2920684403 @default.
- W2920684403 citedByCount "21" @default.
- W2920684403 countsByYear W29206844032018 @default.
- W2920684403 countsByYear W29206844032019 @default.
- W2920684403 countsByYear W29206844032020 @default.
- W2920684403 countsByYear W29206844032021 @default.
- W2920684403 crossrefType "posted-content" @default.
- W2920684403 hasAuthorship W2920684403A5041958651 @default.
- W2920684403 hasAuthorship W2920684403A5044677020 @default.
- W2920684403 hasAuthorship W2920684403A5068127101 @default.
- W2920684403 hasAuthorship W2920684403A5071668416 @default.
- W2920684403 hasAuthorship W2920684403A5088082340 @default.
- W2920684403 hasAuthorship W2920684403A5089890773 @default.
- W2920684403 hasConcept C111472728 @default.
- W2920684403 hasConcept C113364801 @default.
- W2920684403 hasConcept C115961682 @default.
- W2920684403 hasConcept C119599485 @default.
- W2920684403 hasConcept C119857082 @default.
- W2920684403 hasConcept C127413603 @default.
- W2920684403 hasConcept C138885662 @default.
- W2920684403 hasConcept C142362112 @default.
- W2920684403 hasConcept C153349607 @default.
- W2920684403 hasConcept C154945302 @default.
- W2920684403 hasConcept C167966045 @default.
- W2920684403 hasConcept C2776459999 @default.
- W2920684403 hasConcept C2779530757 @default.
- W2920684403 hasConcept C2780616401 @default.
- W2920684403 hasConcept C39890363 @default.
- W2920684403 hasConcept C41008148 @default.
- W2920684403 hasConcept C76155785 @default.
- W2920684403 hasConcept C8038995 @default.
- W2920684403 hasConceptScore W2920684403C111472728 @default.
- W2920684403 hasConceptScore W2920684403C113364801 @default.
- W2920684403 hasConceptScore W2920684403C115961682 @default.
- W2920684403 hasConceptScore W2920684403C119599485 @default.
- W2920684403 hasConceptScore W2920684403C119857082 @default.
- W2920684403 hasConceptScore W2920684403C127413603 @default.
- W2920684403 hasConceptScore W2920684403C138885662 @default.
- W2920684403 hasConceptScore W2920684403C142362112 @default.
- W2920684403 hasConceptScore W2920684403C153349607 @default.
- W2920684403 hasConceptScore W2920684403C154945302 @default.
- W2920684403 hasConceptScore W2920684403C167966045 @default.
- W2920684403 hasConceptScore W2920684403C2776459999 @default.
- W2920684403 hasConceptScore W2920684403C2779530757 @default.
- W2920684403 hasConceptScore W2920684403C2780616401 @default.
- W2920684403 hasConceptScore W2920684403C39890363 @default.