Matches in SemOpenAlex for { <https://semopenalex.org/work/W3006782633> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3006782633 abstract "Data augmentation is one of the most effective approaches for improving the accuracy of modern machine learning models, and it is also indispensable to train a deep model for meta-learning. In this paper, we introduce a task augmentation method by rotating, which increases the number of classes by rotating the original images 90, 180 and 270 degrees, different from traditional augmentation methods which increase the number of images. With a larger amount of classes, we can sample more diverse task instances during training. Therefore, task augmentation by rotating allows us to train a deep network by meta-learning methods with little over-fitting. Experimental results show that our approach is better than the rotation for increasing the number of images and achieves state-of-the-art performance on miniImageNet, CIFAR-FS, and FC100 few-shot learning benchmarks. The code is available on url{this http URL}." @default.
- W3006782633 created "2020-03-06" @default.
- W3006782633 creator A5000389309 @default.
- W3006782633 creator A5076097922 @default.
- W3006782633 creator A5086696969 @default.
- W3006782633 date "2020-02-08" @default.
- W3006782633 modified "2023-10-17" @default.
- W3006782633 title "Task Augmentation by Rotating for Meta-Learning." @default.
- W3006782633 cites W104184427 @default.
- W3006782633 cites W1686810756 @default.
- W3006782633 cites W1904365287 @default.
- W3006782633 cites W2115733720 @default.
- W3006782633 cites W2117539524 @default.
- W3006782633 cites W2194321275 @default.
- W3006782633 cites W2194775991 @default.
- W3006782633 cites W2472819217 @default.
- W3006782633 cites W2601450892 @default.
- W3006782633 cites W2625674597 @default.
- W3006782633 cites W2753160622 @default.
- W3006782633 cites W2762872434 @default.
- W3006782633 cites W2770173563 @default.
- W3006782633 cites W2787501667 @default.
- W3006782633 cites W2798836702 @default.
- W3006782633 cites W2888738308 @default.
- W3006782633 cites W2890166761 @default.
- W3006782633 cites W2892122929 @default.
- W3006782633 cites W2949247522 @default.
- W3006782633 cites W2951696358 @default.
- W3006782633 cites W2962723986 @default.
- W3006782633 cites W2963070905 @default.
- W3006782633 cites W2963078860 @default.
- W3006782633 cites W2963341924 @default.
- W3006782633 cites W2963943197 @default.
- W3006782633 cites W2964112702 @default.
- W3006782633 cites W2964206659 @default.
- W3006782633 cites W2964249870 @default.
- W3006782633 hasPublicationYear "2020" @default.
- W3006782633 type Work @default.
- W3006782633 sameAs 3006782633 @default.
- W3006782633 citedByCount "5" @default.
- W3006782633 countsByYear W30067826332020 @default.
- W3006782633 countsByYear W30067826332021 @default.
- W3006782633 crossrefType "posted-content" @default.
- W3006782633 hasAuthorship W3006782633A5000389309 @default.
- W3006782633 hasAuthorship W3006782633A5076097922 @default.
- W3006782633 hasAuthorship W3006782633A5086696969 @default.
- W3006782633 hasConcept C108583219 @default.
- W3006782633 hasConcept C119857082 @default.
- W3006782633 hasConcept C127413603 @default.
- W3006782633 hasConcept C154945302 @default.
- W3006782633 hasConcept C177264268 @default.
- W3006782633 hasConcept C199360897 @default.
- W3006782633 hasConcept C201995342 @default.
- W3006782633 hasConcept C2776760102 @default.
- W3006782633 hasConcept C2780451532 @default.
- W3006782633 hasConcept C2781002164 @default.
- W3006782633 hasConcept C41008148 @default.
- W3006782633 hasConcept C74050887 @default.
- W3006782633 hasConceptScore W3006782633C108583219 @default.
- W3006782633 hasConceptScore W3006782633C119857082 @default.
- W3006782633 hasConceptScore W3006782633C127413603 @default.
- W3006782633 hasConceptScore W3006782633C154945302 @default.
- W3006782633 hasConceptScore W3006782633C177264268 @default.
- W3006782633 hasConceptScore W3006782633C199360897 @default.
- W3006782633 hasConceptScore W3006782633C201995342 @default.
- W3006782633 hasConceptScore W3006782633C2776760102 @default.
- W3006782633 hasConceptScore W3006782633C2780451532 @default.
- W3006782633 hasConceptScore W3006782633C2781002164 @default.
- W3006782633 hasConceptScore W3006782633C41008148 @default.
- W3006782633 hasConceptScore W3006782633C74050887 @default.
- W3006782633 hasLocation W30067826331 @default.
- W3006782633 hasOpenAccess W3006782633 @default.
- W3006782633 hasPrimaryLocation W30067826331 @default.
- W3006782633 hasRelatedWork W2601450892 @default.
- W3006782633 hasRelatedWork W2894854504 @default.
- W3006782633 hasRelatedWork W2963341924 @default.
- W3006782633 hasRelatedWork W2963459241 @default.
- W3006782633 hasRelatedWork W2963866663 @default.
- W3006782633 hasRelatedWork W2964206659 @default.
- W3006782633 hasRelatedWork W2980742310 @default.
- W3006782633 hasRelatedWork W3013644914 @default.
- W3006782633 hasRelatedWork W3027982633 @default.
- W3006782633 hasRelatedWork W3034911677 @default.
- W3006782633 hasRelatedWork W3041254225 @default.
- W3006782633 hasRelatedWork W3089633463 @default.
- W3006782633 hasRelatedWork W3098814094 @default.
- W3006782633 hasRelatedWork W3126749232 @default.
- W3006782633 hasRelatedWork W3151507536 @default.
- W3006782633 hasRelatedWork W3159328931 @default.
- W3006782633 hasRelatedWork W3161622534 @default.
- W3006782633 hasRelatedWork W3163412989 @default.
- W3006782633 hasRelatedWork W3169141681 @default.
- W3006782633 hasRelatedWork W3177230409 @default.
- W3006782633 isParatext "false" @default.
- W3006782633 isRetracted "false" @default.
- W3006782633 magId "3006782633" @default.
- W3006782633 workType "article" @default.