Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214939412> ?p ?o ?g. }
- W4214939412 endingPage "2253" @default.
- W4214939412 startingPage "2240" @default.
- W4214939412 abstract "Deep learning-based synthetic aperture radar (SAR) image classification is an open problem when training samples are scarce. Transfer learning-based few-shot methods are effective to deal with this problem by transferring knowledge from the electro–optical (EO) to the SAR domain. The performance of such methods relies on extra SAR samples, such as unlabeled novel class’s samples or labeled similar classes samples. However, it is unrealistic to collect sufficient extra SAR samples in some application scenarios, namely the extreme few-shot case. In this case, the performance of such methods degrades seriously. Therefore, few-shot methods that reduce the dependence on extra SAR samples are critical. Motivated by this, a novel few-shot transfer learning method for SAR image classification in the extreme few-shot case is proposed. We propose the connection-free attention module to selectively transfer features shared between EO and SAR samples from a source network to a target network to supplement the loss of information brought by extra SAR samples. Based on the Bayesian convolutional neural network, we propose a training strategy for the extreme few-shot case, which focuses on updating important parameters, namely the accurately updating important parameters. The experimental results on the three real-SAR datasets demonstrate the superiority of our method." @default.
- W4214939412 created "2022-03-05" @default.
- W4214939412 creator A5034682822 @default.
- W4214939412 creator A5044326809 @default.
- W4214939412 creator A5064387292 @default.
- W4214939412 creator A5086504815 @default.
- W4214939412 creator A5090348168 @default.
- W4214939412 date "2022-01-01" @default.
- W4214939412 modified "2023-10-18" @default.
- W4214939412 title "Few-Shot Transfer Learning for SAR Image Classification Without Extra SAR Samples" @default.
- W4214939412 cites W1965572316 @default.
- W4214939412 cites W2029952239 @default.
- W4214939412 cites W2047057213 @default.
- W4214939412 cites W2047229728 @default.
- W4214939412 cites W2103718934 @default.
- W4214939412 cites W2111051539 @default.
- W4214939412 cites W2112796928 @default.
- W4214939412 cites W2194775991 @default.
- W4214939412 cites W2296151615 @default.
- W4214939412 cites W2410591237 @default.
- W4214939412 cites W2752788177 @default.
- W4214939412 cites W2794681092 @default.
- W4214939412 cites W2805508018 @default.
- W4214939412 cites W2912226897 @default.
- W4214939412 cites W2936864631 @default.
- W4214939412 cites W2944029760 @default.
- W4214939412 cites W2963420686 @default.
- W4214939412 cites W2963495494 @default.
- W4214939412 cites W2964137095 @default.
- W4214939412 cites W2990641522 @default.
- W4214939412 cites W2997820257 @default.
- W4214939412 cites W2998270553 @default.
- W4214939412 cites W3034453888 @default.
- W4214939412 cites W3034942609 @default.
- W4214939412 cites W3136341174 @default.
- W4214939412 doi "https://doi.org/10.1109/jstars.2022.3155406" @default.
- W4214939412 hasPublicationYear "2022" @default.
- W4214939412 type Work @default.
- W4214939412 citedByCount "12" @default.
- W4214939412 countsByYear W42149394122022 @default.
- W4214939412 countsByYear W42149394122023 @default.
- W4214939412 crossrefType "journal-article" @default.
- W4214939412 hasAuthorship W4214939412A5034682822 @default.
- W4214939412 hasAuthorship W4214939412A5044326809 @default.
- W4214939412 hasAuthorship W4214939412A5064387292 @default.
- W4214939412 hasAuthorship W4214939412A5086504815 @default.
- W4214939412 hasAuthorship W4214939412A5090348168 @default.
- W4214939412 hasBestOaLocation W42149394121 @default.
- W4214939412 hasConcept C115961682 @default.
- W4214939412 hasConcept C119857082 @default.
- W4214939412 hasConcept C120665830 @default.
- W4214939412 hasConcept C121332964 @default.
- W4214939412 hasConcept C127413603 @default.
- W4214939412 hasConcept C150899416 @default.
- W4214939412 hasConcept C153180895 @default.
- W4214939412 hasConcept C154945302 @default.
- W4214939412 hasConcept C178790620 @default.
- W4214939412 hasConcept C185592680 @default.
- W4214939412 hasConcept C2778344882 @default.
- W4214939412 hasConcept C2992734406 @default.
- W4214939412 hasConcept C3019835501 @default.
- W4214939412 hasConcept C31972630 @default.
- W4214939412 hasConcept C41008148 @default.
- W4214939412 hasConcept C75294576 @default.
- W4214939412 hasConcept C78519656 @default.
- W4214939412 hasConcept C81363708 @default.
- W4214939412 hasConcept C87360688 @default.
- W4214939412 hasConceptScore W4214939412C115961682 @default.
- W4214939412 hasConceptScore W4214939412C119857082 @default.
- W4214939412 hasConceptScore W4214939412C120665830 @default.
- W4214939412 hasConceptScore W4214939412C121332964 @default.
- W4214939412 hasConceptScore W4214939412C127413603 @default.
- W4214939412 hasConceptScore W4214939412C150899416 @default.
- W4214939412 hasConceptScore W4214939412C153180895 @default.
- W4214939412 hasConceptScore W4214939412C154945302 @default.
- W4214939412 hasConceptScore W4214939412C178790620 @default.
- W4214939412 hasConceptScore W4214939412C185592680 @default.
- W4214939412 hasConceptScore W4214939412C2778344882 @default.
- W4214939412 hasConceptScore W4214939412C2992734406 @default.
- W4214939412 hasConceptScore W4214939412C3019835501 @default.
- W4214939412 hasConceptScore W4214939412C31972630 @default.
- W4214939412 hasConceptScore W4214939412C41008148 @default.
- W4214939412 hasConceptScore W4214939412C75294576 @default.
- W4214939412 hasConceptScore W4214939412C78519656 @default.
- W4214939412 hasConceptScore W4214939412C81363708 @default.
- W4214939412 hasConceptScore W4214939412C87360688 @default.
- W4214939412 hasFunder F4320321001 @default.
- W4214939412 hasFunder F4320335787 @default.
- W4214939412 hasLocation W42149394121 @default.
- W4214939412 hasOpenAccess W4214939412 @default.
- W4214939412 hasPrimaryLocation W42149394121 @default.
- W4214939412 hasRelatedWork W2767651786 @default.
- W4214939412 hasRelatedWork W2912288872 @default.
- W4214939412 hasRelatedWork W2996856019 @default.
- W4214939412 hasRelatedWork W3012393889 @default.
- W4214939412 hasRelatedWork W3018421652 @default.
- W4214939412 hasRelatedWork W3021430260 @default.
- W4214939412 hasRelatedWork W3135818718 @default.