Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317761504> ?p ?o ?g. }
- W4317761504 endingPage "18" @default.
- W4317761504 startingPage "1" @default.
- W4317761504 abstract "Few-shot learning (FSL) is an effective method to solve the problem of hyperspectral image (HSI) classification with few labeled samples. It learns transferable knowledge from sufficient labeled auxiliary data to classify unseen classes with limited labeled samples for training. However, the distribution difference between auxiliary data and unseen classes results in the learned transferable knowledge not being well applied to the new task. Therefore, a class-wise attentive cross-domain FSL (CA-CFSL) framework is proposed in this article, in which a feature extractor is learned to extract data features with discriminability and domain invariance. The class-wise attention metric module (CAMM) introduces class-wise attention on the FSL framework to learn more discriminative features, which improves the interclass decision boundaries. Furthermore, an asymmetric domain adversarial module (ADAM) is designed to enhance the ability of extracting domain-invariant representations, which combines asymmetric adversarial training with embedded domain-specific information. Experimental results on four public HSI datasets demonstrate that the proposed method outperforms the existing methods." @default.
- W4317761504 created "2023-01-23" @default.
- W4317761504 creator A5020302879 @default.
- W4317761504 creator A5081560984 @default.
- W4317761504 creator A5085025467 @default.
- W4317761504 creator A5087833114 @default.
- W4317761504 date "2023-01-01" @default.
- W4317761504 modified "2023-10-17" @default.
- W4317761504 title "Cross-Domain Few-Shot Hyperspectral Image Classification With Class-Wise Attention" @default.
- W4317761504 cites W2194775991 @default.
- W4317761504 cites W2212636544 @default.
- W4317761504 cites W2500751094 @default.
- W4317761504 cites W2572303978 @default.
- W4317761504 cites W2620547787 @default.
- W4317761504 cites W2764276316 @default.
- W4317761504 cites W2765268259 @default.
- W4317761504 cites W2773368245 @default.
- W4317761504 cites W2782517596 @default.
- W4317761504 cites W2884821995 @default.
- W4317761504 cites W2898204262 @default.
- W4317761504 cites W2964105864 @default.
- W4317761504 cites W2969181591 @default.
- W4317761504 cites W2976933962 @default.
- W4317761504 cites W3012405452 @default.
- W4317761504 cites W3021632667 @default.
- W4317761504 cites W3023167869 @default.
- W4317761504 cites W3035163205 @default.
- W4317761504 cites W3035667144 @default.
- W4317761504 cites W3043181422 @default.
- W4317761504 cites W3103753223 @default.
- W4317761504 cites W3107591966 @default.
- W4317761504 cites W3109233242 @default.
- W4317761504 cites W3118381885 @default.
- W4317761504 cites W3119997721 @default.
- W4317761504 cites W3122028341 @default.
- W4317761504 cites W3128036660 @default.
- W4317761504 cites W3132867842 @default.
- W4317761504 cites W3138725786 @default.
- W4317761504 cites W3152528485 @default.
- W4317761504 cites W3163842339 @default.
- W4317761504 cites W3169327214 @default.
- W4317761504 cites W3186893889 @default.
- W4317761504 cites W3187443852 @default.
- W4317761504 cites W3189329097 @default.
- W4317761504 cites W3201461236 @default.
- W4317761504 cites W3207208720 @default.
- W4317761504 cites W3214821343 @default.
- W4317761504 cites W4212813030 @default.
- W4317761504 cites W4226043457 @default.
- W4317761504 cites W4283760989 @default.
- W4317761504 doi "https://doi.org/10.1109/tgrs.2023.3239411" @default.
- W4317761504 hasPublicationYear "2023" @default.
- W4317761504 type Work @default.
- W4317761504 citedByCount "0" @default.
- W4317761504 crossrefType "journal-article" @default.
- W4317761504 hasAuthorship W4317761504A5020302879 @default.
- W4317761504 hasAuthorship W4317761504A5081560984 @default.
- W4317761504 hasAuthorship W4317761504A5085025467 @default.
- W4317761504 hasAuthorship W4317761504A5087833114 @default.
- W4317761504 hasConcept C115961682 @default.
- W4317761504 hasConcept C119857082 @default.
- W4317761504 hasConcept C134306372 @default.
- W4317761504 hasConcept C138885662 @default.
- W4317761504 hasConcept C153180895 @default.
- W4317761504 hasConcept C154945302 @default.
- W4317761504 hasConcept C159078339 @default.
- W4317761504 hasConcept C162324750 @default.
- W4317761504 hasConcept C176217482 @default.
- W4317761504 hasConcept C21547014 @default.
- W4317761504 hasConcept C2776401178 @default.
- W4317761504 hasConcept C2777212361 @default.
- W4317761504 hasConcept C33923547 @default.
- W4317761504 hasConcept C36503486 @default.
- W4317761504 hasConcept C41008148 @default.
- W4317761504 hasConcept C41895202 @default.
- W4317761504 hasConcept C52622490 @default.
- W4317761504 hasConcept C75294576 @default.
- W4317761504 hasConcept C97931131 @default.
- W4317761504 hasConceptScore W4317761504C115961682 @default.
- W4317761504 hasConceptScore W4317761504C119857082 @default.
- W4317761504 hasConceptScore W4317761504C134306372 @default.
- W4317761504 hasConceptScore W4317761504C138885662 @default.
- W4317761504 hasConceptScore W4317761504C153180895 @default.
- W4317761504 hasConceptScore W4317761504C154945302 @default.
- W4317761504 hasConceptScore W4317761504C159078339 @default.
- W4317761504 hasConceptScore W4317761504C162324750 @default.
- W4317761504 hasConceptScore W4317761504C176217482 @default.
- W4317761504 hasConceptScore W4317761504C21547014 @default.
- W4317761504 hasConceptScore W4317761504C2776401178 @default.
- W4317761504 hasConceptScore W4317761504C2777212361 @default.
- W4317761504 hasConceptScore W4317761504C33923547 @default.
- W4317761504 hasConceptScore W4317761504C36503486 @default.
- W4317761504 hasConceptScore W4317761504C41008148 @default.
- W4317761504 hasConceptScore W4317761504C41895202 @default.
- W4317761504 hasConceptScore W4317761504C52622490 @default.
- W4317761504 hasConceptScore W4317761504C75294576 @default.
- W4317761504 hasConceptScore W4317761504C97931131 @default.
- W4317761504 hasFunder F4320321001 @default.