FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798381792> ?p ?o ?g. }

• W2798381792 abstract "Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make and model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem in large scale FGVC. Our method won first place in iNaturalist 2017 large scale species classification challenge. Central to the success of our approach is a training scheme that uses higher image resolution and deals with the long-tailed distribution of training data. Next, we study transfer learning via fine-tuning from large scale datasets to small scale, domain-specific FGVC datasets. We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure. Our proposed transfer learning outperforms ImageNet pre-training and obtains state-of-the-art results on multiple commonly used FGVC datasets." @default.
• W2798381792 created "2018-05-07" @default.
• W2798381792 creator A5018609918 @default.
• W2798381792 creator A5037015491 @default.
• W2798381792 creator A5041567418 @default.
• W2798381792 creator A5041864624 @default.
• W2798381792 creator A5060145891 @default.
• W2798381792 date "2018-06-01" @default.
• W2798381792 modified "2023-10-18" @default.
• W2798381792 title "Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning" @default.
• W2798381792 cites W1898560071 @default.
• W2798381792 cites W1941636933 @default.
• W2798381792 cites W1954152232 @default.
• W2798381792 cites W1958236864 @default.
• W2798381792 cites W1994166982 @default.
• W2798381792 cites W2031342017 @default.
• W2798381792 cites W2031489346 @default.
• W2798381792 cites W2034603029 @default.
• W2798381792 cites W2079125479 @default.
• W2798381792 cites W2097117768 @default.
• W2798381792 cites W2102605133 @default.
• W2798381792 cites W2104657103 @default.
• W2798381792 cites W2108598243 @default.
• W2798381792 cites W2117539524 @default.
• W2798381792 cites W2138011018 @default.
• W2798381792 cites W2143668817 @default.
• W2798381792 cites W2161381512 @default.
• W2798381792 cites W2173180041 @default.
• W2798381792 cites W2183341477 @default.
• W2798381792 cites W2194775991 @default.
• W2798381792 cites W2203224402 @default.
• W2798381792 cites W2290566097 @default.
• W2798381792 cites W2398118205 @default.
• W2798381792 cites W2438072089 @default.
• W2798381792 cites W2479109623 @default.
• W2798381792 cites W2533598788 @default.
• W2798381792 cites W2549139847 @default.
• W2798381792 cites W2554320282 @default.
• W2798381792 cites W2737725206 @default.
• W2798381792 cites W2740620254 @default.
• W2798381792 cites W2773003563 @default.
• W2798381792 cites W2780838211 @default.
• W2798381792 cites W2962798895 @default.
• W2798381792 cites W2962843773 @default.
• W2798381792 cites W2963066927 @default.
• W2798381792 cites W2963323244 @default.
• W2798381792 cites W2963426391 @default.
• W2798381792 cites W2963500702 @default.
• W2798381792 cites W2964081807 @default.
• W2798381792 cites W2964275061 @default.
• W2798381792 cites W2964350391 @default.
• W2798381792 cites W3099206234 @default.
• W2798381792 doi "https://doi.org/10.1109/cvpr.2018.00432" @default.
• W2798381792 hasPublicationYear "2018" @default.
• W2798381792 type Work @default.
• W2798381792 sameAs 2798381792 @default.
• W2798381792 citedByCount "291" @default.
• W2798381792 countsByYear W27983817922018 @default.
• W2798381792 countsByYear W27983817922019 @default.
• W2798381792 countsByYear W27983817922020 @default.
• W2798381792 countsByYear W27983817922021 @default.
• W2798381792 countsByYear W27983817922022 @default.
• W2798381792 countsByYear W27983817922023 @default.
• W2798381792 crossrefType "proceedings-article" @default.
• W2798381792 hasAuthorship W2798381792A5018609918 @default.
• W2798381792 hasAuthorship W2798381792A5037015491 @default.
• W2798381792 hasAuthorship W2798381792A5041567418 @default.
• W2798381792 hasAuthorship W2798381792A5041864624 @default.
• W2798381792 hasAuthorship W2798381792A5060145891 @default.
• W2798381792 hasBestOaLocation W27983817922 @default.
• W2798381792 hasConcept C103278499 @default.
• W2798381792 hasConcept C115961682 @default.
• W2798381792 hasConcept C119857082 @default.
• W2798381792 hasConcept C121332964 @default.
• W2798381792 hasConcept C134306372 @default.
• W2798381792 hasConcept C150899416 @default.
• W2798381792 hasConcept C153180895 @default.
• W2798381792 hasConcept C154945302 @default.
• W2798381792 hasConcept C207685749 @default.
• W2798381792 hasConcept C2776321320 @default.
• W2798381792 hasConcept C2778755073 @default.
• W2798381792 hasConcept C33923547 @default.
• W2798381792 hasConcept C36503486 @default.
• W2798381792 hasConcept C41008148 @default.
• W2798381792 hasConcept C62520636 @default.
• W2798381792 hasConcept C94124525 @default.
• W2798381792 hasConceptScore W2798381792C103278499 @default.
• W2798381792 hasConceptScore W2798381792C115961682 @default.
• W2798381792 hasConceptScore W2798381792C119857082 @default.
• W2798381792 hasConceptScore W2798381792C121332964 @default.
• W2798381792 hasConceptScore W2798381792C134306372 @default.
• W2798381792 hasConceptScore W2798381792C150899416 @default.
• W2798381792 hasConceptScore W2798381792C153180895 @default.
• W2798381792 hasConceptScore W2798381792C154945302 @default.
• W2798381792 hasConceptScore W2798381792C207685749 @default.
• W2798381792 hasConceptScore W2798381792C2776321320 @default.
• W2798381792 hasConceptScore W2798381792C2778755073 @default.
• W2798381792 hasConceptScore W2798381792C33923547 @default.
• W2798381792 hasConceptScore W2798381792C36503486 @default.
• W2798381792 hasConceptScore W2798381792C41008148 @default.

• next