Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950649922> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2950649922 abstract "Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples. To employ large models for FGVC without suffering from overfitting, existing methods usually adopt a strategy of pre-training the models using a rich set of auxiliary data, followed by fine-tuning on the target FGVC task. However, the objective of pre-training does not take the target task into account, and consequently such obtained models are suboptimal for fine-tuning. To address this issue, we propose in this paper a new deep FGVC model termed MetaFGNet. Training of MetaFGNet is based on a novel regularized meta-learning objective, which aims to guide the learning of network parameters so that they are optimal for adapting to the target FGVC task. Based on MetaFGNet, we also propose a simple yet effective scheme for selecting more useful samples from the auxiliary data. Experiments on benchmark FGVC datasets show the efficacy of our proposed method." @default.
- W2950649922 created "2019-06-27" @default.
- W2950649922 creator A5024350063 @default.
- W2950649922 creator A5040092039 @default.
- W2950649922 creator A5065964089 @default.
- W2950649922 date "2018-07-28" @default.
- W2950649922 modified "2023-09-23" @default.
- W2950649922 title "Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data" @default.
- W2950649922 cites W1563686443 @default.
- W2950649922 cites W1686810756 @default.
- W2950649922 cites W1797268635 @default.
- W2950649922 cites W1920702274 @default.
- W2950649922 cites W2117539524 @default.
- W2950649922 cites W2165698076 @default.
- W2950649922 cites W2194775991 @default.
- W2950649922 cites W2270409809 @default.
- W2950649922 cites W2289708887 @default.
- W2950649922 cites W2402144811 @default.
- W2950649922 cites W2432717477 @default.
- W2950649922 cites W2604763608 @default.
- W2950649922 cites W2737725206 @default.
- W2950649922 cites W2741910023 @default.
- W2950649922 cites W2753160622 @default.
- W2950649922 cites W2962798895 @default.
- W2950649922 cites W2964176323 @default.
- W2950649922 cites W3091905774 @default.
- W2950649922 cites W14333344 @default.
- W2950649922 doi "https://doi.org/10.48550/arxiv.1807.10916" @default.
- W2950649922 hasPublicationYear "2018" @default.
- W2950649922 type Work @default.
- W2950649922 sameAs 2950649922 @default.
- W2950649922 citedByCount "0" @default.
- W2950649922 crossrefType "posted-content" @default.
- W2950649922 hasAuthorship W2950649922A5024350063 @default.
- W2950649922 hasAuthorship W2950649922A5040092039 @default.
- W2950649922 hasAuthorship W2950649922A5065964089 @default.
- W2950649922 hasBestOaLocation W29506499221 @default.
- W2950649922 hasConcept C119857082 @default.
- W2950649922 hasConcept C13280743 @default.
- W2950649922 hasConcept C134306372 @default.
- W2950649922 hasConcept C154945302 @default.
- W2950649922 hasConcept C162324750 @default.
- W2950649922 hasConcept C177148314 @default.
- W2950649922 hasConcept C177264268 @default.
- W2950649922 hasConcept C185592680 @default.
- W2950649922 hasConcept C185798385 @default.
- W2950649922 hasConcept C187736073 @default.
- W2950649922 hasConcept C198531522 @default.
- W2950649922 hasConcept C199360897 @default.
- W2950649922 hasConcept C205649164 @default.
- W2950649922 hasConcept C22019652 @default.
- W2950649922 hasConcept C2780451532 @default.
- W2950649922 hasConcept C33923547 @default.
- W2950649922 hasConcept C41008148 @default.
- W2950649922 hasConcept C43617362 @default.
- W2950649922 hasConcept C50644808 @default.
- W2950649922 hasConcept C81917197 @default.
- W2950649922 hasConcept C94124525 @default.
- W2950649922 hasConceptScore W2950649922C119857082 @default.
- W2950649922 hasConceptScore W2950649922C13280743 @default.
- W2950649922 hasConceptScore W2950649922C134306372 @default.
- W2950649922 hasConceptScore W2950649922C154945302 @default.
- W2950649922 hasConceptScore W2950649922C162324750 @default.
- W2950649922 hasConceptScore W2950649922C177148314 @default.
- W2950649922 hasConceptScore W2950649922C177264268 @default.
- W2950649922 hasConceptScore W2950649922C185592680 @default.
- W2950649922 hasConceptScore W2950649922C185798385 @default.
- W2950649922 hasConceptScore W2950649922C187736073 @default.
- W2950649922 hasConceptScore W2950649922C198531522 @default.
- W2950649922 hasConceptScore W2950649922C199360897 @default.
- W2950649922 hasConceptScore W2950649922C205649164 @default.
- W2950649922 hasConceptScore W2950649922C22019652 @default.
- W2950649922 hasConceptScore W2950649922C2780451532 @default.
- W2950649922 hasConceptScore W2950649922C33923547 @default.
- W2950649922 hasConceptScore W2950649922C41008148 @default.
- W2950649922 hasConceptScore W2950649922C43617362 @default.
- W2950649922 hasConceptScore W2950649922C50644808 @default.
- W2950649922 hasConceptScore W2950649922C81917197 @default.
- W2950649922 hasConceptScore W2950649922C94124525 @default.
- W2950649922 hasLocation W29506499221 @default.
- W2950649922 hasOpenAccess W2950649922 @default.
- W2950649922 hasPrimaryLocation W29506499221 @default.
- W2950649922 hasRelatedWork W1512413010 @default.
- W2950649922 hasRelatedWork W2346074333 @default.
- W2950649922 hasRelatedWork W2989932438 @default.
- W2950649922 hasRelatedWork W3011996705 @default.
- W2950649922 hasRelatedWork W3034363135 @default.
- W2950649922 hasRelatedWork W3099765033 @default.
- W2950649922 hasRelatedWork W3175189414 @default.
- W2950649922 hasRelatedWork W4210794429 @default.
- W2950649922 hasRelatedWork W4294498805 @default.
- W2950649922 hasRelatedWork W4287758182 @default.
- W2950649922 isParatext "false" @default.
- W2950649922 isRetracted "false" @default.
- W2950649922 magId "2950649922" @default.
- W2950649922 workType "article" @default.