FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2998052623> ?p ?o ?g. }

• W2998052623 endingPage "175" @default.
• W2998052623 startingPage "175" @default.
• W2998052623 abstract "Remote sensing images are featured by massiveness, diversity and complexity. These features put forward higher requirements for the speed and accuracy of remote sensing image retrieval. The extraction method plays a key role in retrieving remote sensing images. Deep metric learning (DML) captures the semantic similarity information between data points by learning embedding in vector space. However, due to the uneven distribution of sample data in remote sensing image datasets, the pair-based loss currently used in DML is not suitable. To improve this, we propose a novel distribution consistency loss to solve this problem. First, we define a new way to mine samples by selecting five in-class hard samples and five inter-class hard samples to form an informative set. This method can make the network extract more useful information in a short time. Secondly, in order to avoid inaccurate feature extraction due to sample imbalance, we assign dynamic weight to the positive samples according to the ratio of the number of hard samples and easy samples in the class, and name the loss caused by the positive sample as the sample balance loss. We combine the sample balance of the positive samples with the ranking consistency of the negative samples to form our distribution consistency loss. Finally, we built an end-to-end fine-tuning network suitable for remote sensing image retrieval. We display comprehensive experimental results drawing on three remote sensing image datasets that are publicly available and show that our method achieves the state-of-the-art performance." @default.
• W2998052623 created "2020-01-10" @default.
• W2998052623 creator A5036072720 @default.
• W2998052623 creator A5041479215 @default.
• W2998052623 creator A5053844211 @default.
• W2998052623 date "2020-01-03" @default.
• W2998052623 modified "2023-10-01" @default.
• W2998052623 title "Distribution Consistency Loss for Large-Scale Remote Sensing Image Retrieval" @default.
• W2998052623 cites W1569769495 @default.
• W2998052623 cites W1783842908 @default.
• W2998052623 cites W1989316905 @default.
• W2998052623 cites W1990537115 @default.
• W2998052623 cites W2019338222 @default.
• W2998052623 cites W2033242207 @default.
• W2998052623 cites W2105032938 @default.
• W2998052623 cites W2248723555 @default.
• W2998052623 cites W2249017129 @default.
• W2998052623 cites W2412782625 @default.
• W2998052623 cites W2544587078 @default.
• W2998052623 cites W2590149631 @default.
• W2998052623 cites W2626107033 @default.
• W2998052623 cites W2750722971 @default.
• W2998052623 cites W2763822693 @default.
• W2998052623 cites W2766938848 @default.
• W2998052623 cites W2767050957 @default.
• W2998052623 cites W2843623251 @default.
• W2998052623 cites W2913741863 @default.
• W2998052623 cites W2942105743 @default.
• W2998052623 cites W2963256013 @default.
• W2998052623 cites W2963588253 @default.
• W2998052623 cites W2976680996 @default.
• W2998052623 cites W2984618269 @default.
• W2998052623 cites W3103856189 @default.
• W2998052623 cites W3105409087 @default.
• W2998052623 cites W3105475654 @default.
• W2998052623 doi "https://doi.org/10.3390/rs12010175" @default.
• W2998052623 hasPublicationYear "2020" @default.
• W2998052623 type Work @default.
• W2998052623 sameAs 2998052623 @default.
• W2998052623 citedByCount "28" @default.
• W2998052623 countsByYear W29980526232020 @default.
• W2998052623 countsByYear W29980526232021 @default.
• W2998052623 countsByYear W29980526232022 @default.
• W2998052623 countsByYear W29980526232023 @default.
• W2998052623 crossrefType "journal-article" @default.
• W2998052623 hasAuthorship W2998052623A5036072720 @default.
• W2998052623 hasAuthorship W2998052623A5041479215 @default.
• W2998052623 hasAuthorship W2998052623A5053844211 @default.
• W2998052623 hasBestOaLocation W29980526231 @default.
• W2998052623 hasConcept C115961682 @default.
• W2998052623 hasConcept C124101348 @default.
• W2998052623 hasConcept C127313418 @default.
• W2998052623 hasConcept C138885662 @default.
• W2998052623 hasConcept C153180895 @default.
• W2998052623 hasConcept C154945302 @default.
• W2998052623 hasConcept C162324750 @default.
• W2998052623 hasConcept C1667742 @default.
• W2998052623 hasConcept C176217482 @default.
• W2998052623 hasConcept C185592680 @default.
• W2998052623 hasConcept C189430467 @default.
• W2998052623 hasConcept C198531522 @default.
• W2998052623 hasConcept C21547014 @default.
• W2998052623 hasConcept C2776401178 @default.
• W2998052623 hasConcept C2776436953 @default.
• W2998052623 hasConcept C41008148 @default.
• W2998052623 hasConcept C41608201 @default.
• W2998052623 hasConcept C41895202 @default.
• W2998052623 hasConcept C43617362 @default.
• W2998052623 hasConcept C62649853 @default.
• W2998052623 hasConcept C83665646 @default.
• W2998052623 hasConceptScore W2998052623C115961682 @default.
• W2998052623 hasConceptScore W2998052623C124101348 @default.
• W2998052623 hasConceptScore W2998052623C127313418 @default.
• W2998052623 hasConceptScore W2998052623C138885662 @default.
• W2998052623 hasConceptScore W2998052623C153180895 @default.
• W2998052623 hasConceptScore W2998052623C154945302 @default.
• W2998052623 hasConceptScore W2998052623C162324750 @default.
• W2998052623 hasConceptScore W2998052623C1667742 @default.
• W2998052623 hasConceptScore W2998052623C176217482 @default.
• W2998052623 hasConceptScore W2998052623C185592680 @default.
• W2998052623 hasConceptScore W2998052623C189430467 @default.
• W2998052623 hasConceptScore W2998052623C198531522 @default.
• W2998052623 hasConceptScore W2998052623C21547014 @default.
• W2998052623 hasConceptScore W2998052623C2776401178 @default.
• W2998052623 hasConceptScore W2998052623C2776436953 @default.
• W2998052623 hasConceptScore W2998052623C41008148 @default.
• W2998052623 hasConceptScore W2998052623C41608201 @default.
• W2998052623 hasConceptScore W2998052623C41895202 @default.
• W2998052623 hasConceptScore W2998052623C43617362 @default.
• W2998052623 hasConceptScore W2998052623C62649853 @default.
• W2998052623 hasConceptScore W2998052623C83665646 @default.
• W2998052623 hasFunder F4320335595 @default.
• W2998052623 hasFunder F4320335880 @default.
• W2998052623 hasIssue "1" @default.
• W2998052623 hasLocation W29980526231 @default.
• W2998052623 hasOpenAccess W2998052623 @default.
• W2998052623 hasPrimaryLocation W29980526231 @default.
• W2998052623 hasRelatedWork W2027614354 @default.

• next