Matches in SemOpenAlex for { <https://semopenalex.org/work/W3007788656> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3007788656 endingPage "792" @default.
- W3007788656 startingPage "779" @default.
- W3007788656 abstract "Recognizing images from subcategories with subtle differences remains a challenging task due to the scarcity of quantity and diversity of training samples. Existing data augmentation methods either rely on models trained with fully annotated data or involve human in the loop, which is labor-intensive. In this paper, we propose a simple approach that leverages large amounts of noisy images from the Web for fine-grained image classification. Beginning with a deep model taken as input image patches for feature representation, the maximum entropy learning criterion is first introduced to improve the score-based patch selection. Then a noise removal procedure is designed to verify the usefulness of noisy images in the augmented data for classification. Extensive experiments on standard, augmented, and combined datasets with and without noise validate the effectiveness of our method. Generally, we achieve comparable results on benchmark datasets, e.g., CUB-Birds, Stanford Dogs, and Stanford Cars, with only 50 augmented noisy samples for every category." @default.
- W3007788656 created "2020-03-06" @default.
- W3007788656 creator A5023583572 @default.
- W3007788656 creator A5029205920 @default.
- W3007788656 creator A5057841204 @default.
- W3007788656 creator A5070235642 @default.
- W3007788656 creator A5085342186 @default.
- W3007788656 date "2020-01-01" @default.
- W3007788656 modified "2023-09-27" @default.
- W3007788656 title "The Effectiveness of Noise in Data Augmentation for Fine-Grained Image Classification" @default.
- W3007788656 cites W1531492214 @default.
- W3007788656 cites W1849277567 @default.
- W3007788656 cites W1929903369 @default.
- W3007788656 cites W1980526845 @default.
- W3007788656 cites W1984514441 @default.
- W3007788656 cites W1995543189 @default.
- W3007788656 cites W2097117768 @default.
- W3007788656 cites W2102605133 @default.
- W3007788656 cites W2108598243 @default.
- W3007788656 cites W2118696714 @default.
- W3007788656 cites W2135706578 @default.
- W3007788656 cites W2138011018 @default.
- W3007788656 cites W2165698076 @default.
- W3007788656 cites W2194775991 @default.
- W3007788656 cites W2196615847 @default.
- W3007788656 cites W2287418003 @default.
- W3007788656 cites W2737725206 @default.
- W3007788656 cites W2773003563 @default.
- W3007788656 cites W2798365843 @default.
- W3007788656 cites W2798381792 @default.
- W3007788656 cites W2807931652 @default.
- W3007788656 cites W2882999943 @default.
- W3007788656 cites W2891951760 @default.
- W3007788656 cites W2962798895 @default.
- W3007788656 cites W56385144 @default.
- W3007788656 doi "https://doi.org/10.1007/978-3-030-41404-7_55" @default.
- W3007788656 hasPublicationYear "2020" @default.
- W3007788656 type Work @default.
- W3007788656 sameAs 3007788656 @default.
- W3007788656 citedByCount "3" @default.
- W3007788656 countsByYear W30077886562021 @default.
- W3007788656 countsByYear W30077886562022 @default.
- W3007788656 crossrefType "book-chapter" @default.
- W3007788656 hasAuthorship W3007788656A5023583572 @default.
- W3007788656 hasAuthorship W3007788656A5029205920 @default.
- W3007788656 hasAuthorship W3007788656A5057841204 @default.
- W3007788656 hasAuthorship W3007788656A5070235642 @default.
- W3007788656 hasAuthorship W3007788656A5085342186 @default.
- W3007788656 hasConcept C106301342 @default.
- W3007788656 hasConcept C115961682 @default.
- W3007788656 hasConcept C119857082 @default.
- W3007788656 hasConcept C121332964 @default.
- W3007788656 hasConcept C13280743 @default.
- W3007788656 hasConcept C153180895 @default.
- W3007788656 hasConcept C154945302 @default.
- W3007788656 hasConcept C185798385 @default.
- W3007788656 hasConcept C205649164 @default.
- W3007788656 hasConcept C41008148 @default.
- W3007788656 hasConcept C62520636 @default.
- W3007788656 hasConcept C99498987 @default.
- W3007788656 hasConceptScore W3007788656C106301342 @default.
- W3007788656 hasConceptScore W3007788656C115961682 @default.
- W3007788656 hasConceptScore W3007788656C119857082 @default.
- W3007788656 hasConceptScore W3007788656C121332964 @default.
- W3007788656 hasConceptScore W3007788656C13280743 @default.
- W3007788656 hasConceptScore W3007788656C153180895 @default.
- W3007788656 hasConceptScore W3007788656C154945302 @default.
- W3007788656 hasConceptScore W3007788656C185798385 @default.
- W3007788656 hasConceptScore W3007788656C205649164 @default.
- W3007788656 hasConceptScore W3007788656C41008148 @default.
- W3007788656 hasConceptScore W3007788656C62520636 @default.
- W3007788656 hasConceptScore W3007788656C99498987 @default.
- W3007788656 hasLocation W30077886561 @default.
- W3007788656 hasOpenAccess W3007788656 @default.
- W3007788656 hasPrimaryLocation W30077886561 @default.
- W3007788656 hasRelatedWork W112744582 @default.
- W3007788656 hasRelatedWork W1485630101 @default.
- W3007788656 hasRelatedWork W2498017833 @default.
- W3007788656 hasRelatedWork W2897410528 @default.
- W3007788656 hasRelatedWork W2948131761 @default.
- W3007788656 hasRelatedWork W2961085424 @default.
- W3007788656 hasRelatedWork W3081841992 @default.
- W3007788656 hasRelatedWork W3205677146 @default.
- W3007788656 hasRelatedWork W4306674287 @default.
- W3007788656 hasRelatedWork W4224009465 @default.
- W3007788656 isParatext "false" @default.
- W3007788656 isRetracted "false" @default.
- W3007788656 magId "3007788656" @default.
- W3007788656 workType "book-chapter" @default.