FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080919303> ?p ?o ?g. }

• W3080919303 endingPage "5053" @default.
• W3080919303 startingPage "5040" @default.
• W3080919303 abstract "In recent years, hyperspectral image (HSI) classification based on generative adversarial networks (GAN) has achieved great progress. GAN-based classification methods can mitigate the limited training sample dilemma to some extent. However, several studies have pointed out that existing GAN-based HSI classification methods are heavily affected by the imbalanced training data problem. The discriminator in GAN always contradicts itself and tries to associate fake labels to the minority-class samples, and thus impair the classification performance. Another critical issue is the mode collapse in GAN-based methods. The generator is only capable of producing samples within a narrow scope of the data space, which severely hinders the advancement of GAN-based HSI classification methods. In this paper, we proposed an Adaptive DropBlock-enhanced Generative Adversarial Networks (ADGAN) for HSI classification. First, to solve the imbalanced training data problem, we adjust the discriminator to be a single classifier, and it will not contradict itself. Second, an adaptive DropBlock (AdapDrop) is proposed as a regularization method employed in the generator and discriminator to alleviate the mode collapse issue. The AdapDrop generated drop masks with adaptive shapes instead of a fixed size region, and it alleviates the limitations of DropBlock in dealing with ground objects with various shapes. Experimental results on three HSI datasets demonstrated that the proposed ADGAN achieved superior performance over state-of-the-art GAN-based methods. Our codes are available at https://github.com/summitgao/HC_ADGAN" @default.
• W3080919303 created "2020-09-01" @default.
• W3080919303 creator A5029633264 @default.
• W3080919303 creator A5033017179 @default.
• W3080919303 creator A5046668357 @default.
• W3080919303 creator A5048989648 @default.
• W3080919303 date "2021-06-01" @default.
• W3080919303 modified "2023-10-16" @default.
• W3080919303 title "Adaptive DropBlock-Enhanced Generative Adversarial Networks for Hyperspectral Image Classification" @default.
• W3080919303 cites W1515353041 @default.
• W3080919303 cites W1939429412 @default.
• W3080919303 cites W1991576946 @default.
• W3080919303 cites W2004104348 @default.
• W3080919303 cites W2004491663 @default.
• W3080919303 cites W2014327494 @default.
• W3080919303 cites W2029316659 @default.
• W3080919303 cites W2043665634 @default.
• W3080919303 cites W2045757377 @default.
• W3080919303 cites W2049003564 @default.
• W3080919303 cites W2059089906 @default.
• W3080919303 cites W2090424610 @default.
• W3080919303 cites W2097117768 @default.
• W3080919303 cites W2101711129 @default.
• W3080919303 cites W2102605133 @default.
• W3080919303 cites W2105386417 @default.
• W3080919303 cites W2114819256 @default.
• W3080919303 cites W2152057649 @default.
• W3080919303 cites W2155658307 @default.
• W3080919303 cites W2156316030 @default.
• W3080919303 cites W2160815625 @default.
• W3080919303 cites W2166923144 @default.
• W3080919303 cites W2344173806 @default.
• W3080919303 cites W2500751094 @default.
• W3080919303 cites W2518831014 @default.
• W3080919303 cites W2565258258 @default.
• W3080919303 cites W2577238056 @default.
• W3080919303 cites W2587790406 @default.
• W3080919303 cites W2608092940 @default.
• W3080919303 cites W2764276316 @default.
• W3080919303 cites W2767651786 @default.
• W3080919303 cites W2768211636 @default.
• W3080919303 cites W2777427437 @default.
• W3080919303 cites W2791006446 @default.
• W3080919303 cites W2794472454 @default.
• W3080919303 cites W2806437580 @default.
• W3080919303 cites W2907100627 @default.
• W3080919303 cites W2921445432 @default.
• W3080919303 cites W2941387379 @default.
• W3080919303 cites W2944413439 @default.
• W3080919303 cites W2949034001 @default.
• W3080919303 cites W2950266692 @default.
• W3080919303 cites W2963706720 @default.
• W3080919303 cites W2964081807 @default.
• W3080919303 cites W3099831940 @default.
• W3080919303 doi "https://doi.org/10.1109/tgrs.2020.3015843" @default.
• W3080919303 hasPublicationYear "2021" @default.
• W3080919303 type Work @default.
• W3080919303 sameAs 3080919303 @default.
• W3080919303 citedByCount "34" @default.
• W3080919303 countsByYear W30809193032020 @default.
• W3080919303 countsByYear W30809193032021 @default.
• W3080919303 countsByYear W30809193032022 @default.
• W3080919303 countsByYear W30809193032023 @default.
• W3080919303 crossrefType "journal-article" @default.
• W3080919303 hasAuthorship W3080919303A5029633264 @default.
• W3080919303 hasAuthorship W3080919303A5033017179 @default.
• W3080919303 hasAuthorship W3080919303A5046668357 @default.
• W3080919303 hasAuthorship W3080919303A5048989648 @default.
• W3080919303 hasBestOaLocation W30809193032 @default.
• W3080919303 hasConcept C115961682 @default.
• W3080919303 hasConcept C119857082 @default.
• W3080919303 hasConcept C121332964 @default.
• W3080919303 hasConcept C153180895 @default.
• W3080919303 hasConcept C154945302 @default.
• W3080919303 hasConcept C159078339 @default.
• W3080919303 hasConcept C163258240 @default.
• W3080919303 hasConcept C174348530 @default.
• W3080919303 hasConcept C2779803651 @default.
• W3080919303 hasConcept C2780992000 @default.
• W3080919303 hasConcept C31258907 @default.
• W3080919303 hasConcept C41008148 @default.
• W3080919303 hasConcept C41608201 @default.
• W3080919303 hasConcept C62520636 @default.
• W3080919303 hasConcept C75294576 @default.
• W3080919303 hasConcept C76155785 @default.
• W3080919303 hasConcept C94915269 @default.
• W3080919303 hasConcept C95623464 @default.
• W3080919303 hasConceptScore W3080919303C115961682 @default.
• W3080919303 hasConceptScore W3080919303C119857082 @default.
• W3080919303 hasConceptScore W3080919303C121332964 @default.
• W3080919303 hasConceptScore W3080919303C153180895 @default.
• W3080919303 hasConceptScore W3080919303C154945302 @default.
• W3080919303 hasConceptScore W3080919303C159078339 @default.
• W3080919303 hasConceptScore W3080919303C163258240 @default.
• W3080919303 hasConceptScore W3080919303C174348530 @default.
• W3080919303 hasConceptScore W3080919303C2779803651 @default.
• W3080919303 hasConceptScore W3080919303C2780992000 @default.
• W3080919303 hasConceptScore W3080919303C31258907 @default.

• next