FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361859093> ?p ?o ?g. }

• W4361859093 endingPage "4606" @default.
• W4361859093 startingPage "4591" @default.
• W4361859093 abstract "Few-shot learning, which aims to learn the concept of novel category from extremely limited labeled samples, has received intense interests in remote sensing image scene classification. Most of the existing methods inherit the philosophy of prototype learning and tackle classification as the prototype-based metric matching problem. Despite the achievement that has been obtained so far, the problems of interclass metric misalignment and intraclass variations have become two main challenges that obstacle the performance. In this paper, a novel transductive learning framework with conditional metric embedding is proposed to remedy these problems. First, a conditional metric embedding mechanism is introduced to perform anisotropic embedding for each pair of the support category and query instance. This design provides the model with flexible scalability to accommodate the metric biases across classes. Second, a transductive prototype learning strategy is presented to enhance the robustness of the prototype against intraclass variations. The unlabeled query instances are transformed into pseudo instances equipped with credibility coefficients and then leveraged to calibrate the prototype estimation bias in low data regimes. Third, a long-term consistency regularization is designed, which continuously memorizes the historical prototypes to generate additional supervision of interclass separation in the global label space. Benefiting from this design, the discriminability of the prototypes obtains obvious improvement. Finally, extensive experiments are conducted on three public benchmark remote sensing datasets. The experimental results demonstrate the validity and the superiority of the proposed method in low-shot conditions." @default.
• W4361859093 created "2023-04-05" @default.
• W4361859093 creator A5001093841 @default.
• W4361859093 creator A5002059265 @default.
• W4361859093 creator A5005905514 @default.
• W4361859093 creator A5023538862 @default.
• W4361859093 creator A5032046883 @default.
• W4361859093 creator A5089689930 @default.
• W4361859093 date "2023-01-01" @default.
• W4361859093 modified "2023-10-10" @default.
• W4361859093 title "TDNet: A Novel Transductive Learning Framework With Conditional Metric Embedding for Few-Shot Remote Sensing Image Scene Classification" @default.
• W4361859093 cites W2115733720 @default.
• W4361859093 cites W2145680191 @default.
• W4361859093 cites W2151103935 @default.
• W4361859093 cites W2163352848 @default.
• W4361859093 cites W2253590344 @default.
• W4361859093 cites W2577537809 @default.
• W4361859093 cites W2783165089 @default.
• W4361859093 cites W2890732922 @default.
• W4361859093 cites W2895094948 @default.
• W4361859093 cites W2909158354 @default.
• W4361859093 cites W2914885528 @default.
• W4361859093 cites W2943216879 @default.
• W4361859093 cites W2963078860 @default.
• W4361859093 cites W2963283377 @default.
• W4361859093 cites W2964105864 @default.
• W4361859093 cites W2966415767 @default.
• W4361859093 cites W2974770574 @default.
• W4361859093 cites W2979301925 @default.
• W4361859093 cites W2979805229 @default.
• W4361859093 cites W2983156430 @default.
• W4361859093 cites W2990230185 @default.
• W4361859093 cites W3022140654 @default.
• W4361859093 cites W3025346498 @default.
• W4361859093 cites W3034942609 @default.
• W4361859093 cites W3080181119 @default.
• W4361859093 cites W3086451439 @default.
• W4361859093 cites W3095691842 @default.
• W4361859093 cites W3096675569 @default.
• W4361859093 cites W3096805028 @default.
• W4361859093 cites W3103856189 @default.
• W4361859093 cites W3105577662 @default.
• W4361859093 cites W3119804198 @default.
• W4361859093 cites W3126133447 @default.
• W4361859093 cites W3127899546 @default.
• W4361859093 cites W3131937156 @default.
• W4361859093 cites W3188824417 @default.
• W4361859093 cites W3191036819 @default.
• W4361859093 cites W3199708111 @default.
• W4361859093 cites W3204731106 @default.
• W4361859093 cites W3213288046 @default.
• W4361859093 cites W4206554021 @default.
• W4361859093 cites W4210997624 @default.
• W4361859093 cites W4212897988 @default.
• W4361859093 cites W4214725994 @default.
• W4361859093 cites W4221153269 @default.
• W4361859093 cites W4280563105 @default.
• W4361859093 cites W4283760989 @default.
• W4361859093 cites W4285157526 @default.
• W4361859093 cites W4285817614 @default.
• W4361859093 cites W4289792768 @default.
• W4361859093 cites W4293732058 @default.
• W4361859093 doi "https://doi.org/10.1109/jstars.2023.3263149" @default.
• W4361859093 hasPublicationYear "2023" @default.
• W4361859093 type Work @default.
• W4361859093 citedByCount "0" @default.
• W4361859093 crossrefType "journal-article" @default.
• W4361859093 hasAuthorship W4361859093A5001093841 @default.
• W4361859093 hasAuthorship W4361859093A5002059265 @default.
• W4361859093 hasAuthorship W4361859093A5005905514 @default.
• W4361859093 hasAuthorship W4361859093A5023538862 @default.
• W4361859093 hasAuthorship W4361859093A5032046883 @default.
• W4361859093 hasAuthorship W4361859093A5089689930 @default.
• W4361859093 hasBestOaLocation W43618590931 @default.
• W4361859093 hasConcept C104317684 @default.
• W4361859093 hasConcept C115961682 @default.
• W4361859093 hasConcept C119857082 @default.
• W4361859093 hasConcept C153180895 @default.
• W4361859093 hasConcept C154945302 @default.
• W4361859093 hasConcept C162324750 @default.
• W4361859093 hasConcept C176217482 @default.
• W4361859093 hasConcept C185592680 @default.
• W4361859093 hasConcept C21547014 @default.
• W4361859093 hasConcept C2776135515 @default.
• W4361859093 hasConcept C41008148 @default.
• W4361859093 hasConcept C41608201 @default.
• W4361859093 hasConcept C48044578 @default.
• W4361859093 hasConcept C55493867 @default.
• W4361859093 hasConcept C63479239 @default.
• W4361859093 hasConcept C75294576 @default.
• W4361859093 hasConcept C77088390 @default.
• W4361859093 hasConceptScore W4361859093C104317684 @default.
• W4361859093 hasConceptScore W4361859093C115961682 @default.
• W4361859093 hasConceptScore W4361859093C119857082 @default.
• W4361859093 hasConceptScore W4361859093C153180895 @default.
• W4361859093 hasConceptScore W4361859093C154945302 @default.
• W4361859093 hasConceptScore W4361859093C162324750 @default.
• W4361859093 hasConceptScore W4361859093C176217482 @default.

• next