Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204330110> ?p ?o ?g. }
- W3204330110 abstract "Internal learning for single-image generation is a framework, where a generator is trained to produce novel images based on a single image. Since these models are trained on a single image, they are limited in their scale and application. To overcome these issues, we propose a meta-learning approach that enables training over a collection of images, in order to model the internal statistics of the sample image more effectively. In the presented meta-learning approach, a single-image GAN model is generated given an input image, via a convolutional feedforward hypernetwork $f$. This network is trained over a dataset of images, allowing for feature sharing among different models, and for interpolation in the space of generative models. The generated single-image model contains a hierarchy of multiple generators and discriminators. It is therefore required to train the meta-learner in an adversarial manner, which requires careful design choices that we justify by a theoretical analysis. Our results show that the models obtained are as suitable as single-image GANs for many common image applications, significantly reduce the training time per image without loss in performance, and introduce novel capabilities, such as interpolation and feedforward modeling of novel images." @default.
- W3204330110 created "2021-10-11" @default.
- W3204330110 creator A5011488127 @default.
- W3204330110 creator A5045895297 @default.
- W3204330110 creator A5050776111 @default.
- W3204330110 creator A5078102229 @default.
- W3204330110 date "2021-10-06" @default.
- W3204330110 modified "2023-09-27" @default.
- W3204330110 title "Meta Internal Learning." @default.
- W3204330110 cites W1522301498 @default.
- W3204330110 cites W1677182931 @default.
- W3204330110 cites W1988115241 @default.
- W3204330110 cites W2079224763 @default.
- W3204330110 cites W2103496339 @default.
- W3204330110 cites W2118774596 @default.
- W3204330110 cites W2134670479 @default.
- W3204330110 cites W2152593035 @default.
- W3204330110 cites W2275363859 @default.
- W3204330110 cites W2339754110 @default.
- W3204330110 cites W2595713799 @default.
- W3204330110 cites W2604763608 @default.
- W3204330110 cites W2739748921 @default.
- W3204330110 cites W2766099245 @default.
- W3204330110 cites W2771305881 @default.
- W3204330110 cites W2786022758 @default.
- W3204330110 cites W2912119436 @default.
- W3204330110 cites W2962770929 @default.
- W3204330110 cites W2962810352 @default.
- W3204330110 cites W2962879692 @default.
- W3204330110 cites W2963073614 @default.
- W3204330110 cites W2963097630 @default.
- W3204330110 cites W2963137684 @default.
- W3204330110 cites W2963285940 @default.
- W3204330110 cites W2963485221 @default.
- W3204330110 cites W2963704386 @default.
- W3204330110 cites W2964019104 @default.
- W3204330110 cites W2982006683 @default.
- W3204330110 cites W2982041717 @default.
- W3204330110 cites W2996144997 @default.
- W3204330110 cites W3009014607 @default.
- W3204330110 cites W3013634494 @default.
- W3204330110 cites W3036234074 @default.
- W3204330110 cites W3036344793 @default.
- W3204330110 cites W3040618924 @default.
- W3204330110 cites W3099920963 @default.
- W3204330110 cites W3119439276 @default.
- W3204330110 hasPublicationYear "2021" @default.
- W3204330110 type Work @default.
- W3204330110 sameAs 3204330110 @default.
- W3204330110 citedByCount "0" @default.
- W3204330110 crossrefType "posted-content" @default.
- W3204330110 hasAuthorship W3204330110A5011488127 @default.
- W3204330110 hasAuthorship W3204330110A5045895297 @default.
- W3204330110 hasAuthorship W3204330110A5050776111 @default.
- W3204330110 hasAuthorship W3204330110A5078102229 @default.
- W3204330110 hasConcept C115961682 @default.
- W3204330110 hasConcept C119857082 @default.
- W3204330110 hasConcept C121332964 @default.
- W3204330110 hasConcept C127413603 @default.
- W3204330110 hasConcept C133731056 @default.
- W3204330110 hasConcept C137800194 @default.
- W3204330110 hasConcept C138885662 @default.
- W3204330110 hasConcept C153180895 @default.
- W3204330110 hasConcept C154945302 @default.
- W3204330110 hasConcept C163258240 @default.
- W3204330110 hasConcept C27405340 @default.
- W3204330110 hasConcept C2776401178 @default.
- W3204330110 hasConcept C2780992000 @default.
- W3204330110 hasConcept C31972630 @default.
- W3204330110 hasConcept C38858127 @default.
- W3204330110 hasConcept C41008148 @default.
- W3204330110 hasConcept C41895202 @default.
- W3204330110 hasConcept C62520636 @default.
- W3204330110 hasConcept C9417928 @default.
- W3204330110 hasConceptScore W3204330110C115961682 @default.
- W3204330110 hasConceptScore W3204330110C119857082 @default.
- W3204330110 hasConceptScore W3204330110C121332964 @default.
- W3204330110 hasConceptScore W3204330110C127413603 @default.
- W3204330110 hasConceptScore W3204330110C133731056 @default.
- W3204330110 hasConceptScore W3204330110C137800194 @default.
- W3204330110 hasConceptScore W3204330110C138885662 @default.
- W3204330110 hasConceptScore W3204330110C153180895 @default.
- W3204330110 hasConceptScore W3204330110C154945302 @default.
- W3204330110 hasConceptScore W3204330110C163258240 @default.
- W3204330110 hasConceptScore W3204330110C27405340 @default.
- W3204330110 hasConceptScore W3204330110C2776401178 @default.
- W3204330110 hasConceptScore W3204330110C2780992000 @default.
- W3204330110 hasConceptScore W3204330110C31972630 @default.
- W3204330110 hasConceptScore W3204330110C38858127 @default.
- W3204330110 hasConceptScore W3204330110C41008148 @default.
- W3204330110 hasConceptScore W3204330110C41895202 @default.
- W3204330110 hasConceptScore W3204330110C62520636 @default.
- W3204330110 hasConceptScore W3204330110C9417928 @default.
- W3204330110 hasLocation W32043301101 @default.
- W3204330110 hasOpenAccess W3204330110 @default.
- W3204330110 hasPrimaryLocation W32043301101 @default.
- W3204330110 hasRelatedWork W2567101557 @default.
- W3204330110 hasRelatedWork W2963767194 @default.
- W3204330110 hasRelatedWork W2969789619 @default.
- W3204330110 hasRelatedWork W2984648456 @default.