FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313576755> ?p ?o ?g. }

• W4313576755 endingPage "304" @default.
• W4313576755 startingPage "304" @default.
• W4313576755 abstract "Hyperspectral images contain rich features in both spectral and spatial domains, which bring opportunities for accurate recognition of similar materials and promote various fine-grained remote sensing applications. Although deep learning models have been extensively investigated in the field of hyperspectral image classification (HSIC) tasks, classification performance is still limited under small sample conditions, and this has been a longstanding problem. The features extracted by complex network structures with large model size are redundant to some extent and prone to overfitting. This paper proposes a low-rank constrained attention-enhanced multiple feature fusion network (LAMFN). Firstly, factor analysis is used to extract very few components that can describe the original data using covariance information to perform spectral feature preprocessing. Then, a lightweight attention-enhanced 3D convolution module is used for deep feature extraction, and the position-sensitive information is supplemented using a 2D coordinate attention. The above widely varying spatial–spectral feature groups are fused through a simple composite residual structure. Finally, low-rank second-order pooling is adopted to enhance the convolutional feature selectivity and achieve classification. Extensive experiments were conducted on four representative hyperspectral datasets with different spatial–spectral characteristics, namely Indian Pines (IP), Pavia Center (PC), Houston (HU), and WHU-HongHu (WHU). The contrast methods include several advanced models proposed recently, including residual CNNs, attention-based CNNs, and transformer-based models. Using only five samples per class for training, LAMFN achieved overall accuracies of 78.15%, 97.18%, 81.35%, and 87.93% on the above datasets, which has an improvement of 0.82%, 1.12%, 1.67%, and 0.89% compared to the second-best model. The running time of LAMFN is moderate. For example, the training time of LAMFN on the WHU dataset was 29.1 s, and the contrast models ranged from 3.0 s to 341.4 s. In addition, ablation experiments and comparisons with some advanced semi-supervised learning methods further validated the effectiveness of the proposed model designs." @default.
• W4313576755 created "2023-01-06" @default.
• W4313576755 creator A5035085609 @default.
• W4313576755 creator A5039991862 @default.
• W4313576755 creator A5055174519 @default.
• W4313576755 creator A5072479287 @default.
• W4313576755 date "2023-01-04" @default.
• W4313576755 modified "2023-09-30" @default.
• W4313576755 title "Low-Rank Constrained Attention-Enhanced Multiple Spatial–Spectral Feature Fusion for Small Sample Hyperspectral Image Classification" @default.
• W4313576755 cites W1966580635 @default.
• W4313576755 cites W2500751094 @default.
• W4313576755 cites W2554320282 @default.
• W4313576755 cites W2757208835 @default.
• W4313576755 cites W2764276316 @default.
• W4313576755 cites W2792332881 @default.
• W4313576755 cites W2801324747 @default.
• W4313576755 cites W2822065499 @default.
• W4313576755 cites W2884585870 @default.
• W4313576755 cites W2894165434 @default.
• W4313576755 cites W2898204262 @default.
• W4313576755 cites W2914331134 @default.
• W4313576755 cites W2962702700 @default.
• W4313576755 cites W2963420686 @default.
• W4313576755 cites W2963495494 @default.
• W4313576755 cites W2977002487 @default.
• W4313576755 cites W2980598835 @default.
• W4313576755 cites W2982083293 @default.
• W4313576755 cites W2991575127 @default.
• W4313576755 cites W2997294353 @default.
• W4313576755 cites W3003552243 @default.
• W4313576755 cites W3012405452 @default.
• W4313576755 cites W3014253313 @default.
• W4313576755 cites W3017845037 @default.
• W4313576755 cites W3021805542 @default.
• W4313576755 cites W3031696400 @default.
• W4313576755 cites W3047317383 @default.
• W4313576755 cites W3049655825 @default.
• W4313576755 cites W3086507804 @default.
• W4313576755 cites W3099850646 @default.
• W4313576755 cites W3100932715 @default.
• W4313576755 cites W3103753223 @default.
• W4313576755 cites W3114720220 @default.
• W4313576755 cites W3114798932 @default.
• W4313576755 cites W3120356488 @default.
• W4313576755 cites W3122028341 @default.
• W4313576755 cites W3122774149 @default.
• W4313576755 cites W3138725786 @default.
• W4313576755 cites W3177052299 @default.
• W4313576755 cites W3192416785 @default.
• W4313576755 cites W3192731655 @default.
• W4313576755 cites W3198155834 @default.
• W4313576755 cites W3207818847 @default.
• W4313576755 cites W3212386989 @default.
• W4313576755 cites W4207006012 @default.
• W4313576755 cites W4210524687 @default.
• W4313576755 cites W4220727424 @default.
• W4313576755 cites W4226334005 @default.
• W4313576755 cites W4229042884 @default.
• W4313576755 cites W4281568429 @default.
• W4313576755 cites W4285127355 @default.
• W4313576755 cites W4292257555 @default.
• W4313576755 cites W4312443924 @default.
• W4313576755 cites W4312743284 @default.
• W4313576755 doi "https://doi.org/10.3390/rs15020304" @default.
• W4313576755 hasPublicationYear "2023" @default.
• W4313576755 type Work @default.
• W4313576755 citedByCount "1" @default.
• W4313576755 countsByYear W43135767552023 @default.
• W4313576755 crossrefType "journal-article" @default.
• W4313576755 hasAuthorship W4313576755A5035085609 @default.
• W4313576755 hasAuthorship W4313576755A5039991862 @default.
• W4313576755 hasAuthorship W4313576755A5055174519 @default.
• W4313576755 hasAuthorship W4313576755A5072479287 @default.
• W4313576755 hasBestOaLocation W43135767551 @default.
• W4313576755 hasConcept C11413529 @default.
• W4313576755 hasConcept C127313418 @default.
• W4313576755 hasConcept C138885662 @default.
• W4313576755 hasConcept C153180895 @default.
• W4313576755 hasConcept C154945302 @default.
• W4313576755 hasConcept C155512373 @default.
• W4313576755 hasConcept C159078339 @default.
• W4313576755 hasConcept C22019652 @default.
• W4313576755 hasConcept C2776401178 @default.
• W4313576755 hasConcept C34736171 @default.
• W4313576755 hasConcept C41008148 @default.
• W4313576755 hasConcept C41895202 @default.
• W4313576755 hasConcept C50644808 @default.
• W4313576755 hasConcept C52622490 @default.
• W4313576755 hasConcept C62649853 @default.
• W4313576755 hasConcept C81363708 @default.
• W4313576755 hasConceptScore W4313576755C11413529 @default.
• W4313576755 hasConceptScore W4313576755C127313418 @default.
• W4313576755 hasConceptScore W4313576755C138885662 @default.
• W4313576755 hasConceptScore W4313576755C153180895 @default.
• W4313576755 hasConceptScore W4313576755C154945302 @default.
• W4313576755 hasConceptScore W4313576755C155512373 @default.
• W4313576755 hasConceptScore W4313576755C159078339 @default.
• W4313576755 hasConceptScore W4313576755C22019652 @default.

• next