Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285200322> ?p ?o ?g. }
- W4285200322 endingPage "14" @default.
- W4285200322 startingPage "1" @default.
- W4285200322 abstract "With the rapid development of deep learning, the convolutional neural networks (CNNs) have been widely used in hyperspectral image classification (HSIC) and achieved excellent performance. However, CNNs reuse the same kernel weights over different locations, resulting in the insufficient capability of capturing diversity spatial interactions. Moreover, CNNs usually require a large amount of training samples to optimize the learnable parameters. When training samples are limited, the classification performance of CNN tends to drop off a cliff. To tackle the aforementioned issues, a novel residual spatial attention kernel generation network (RSAKGN) is proposed for HSIC. First, a spatial attention kernel generation module (SAKGM) is built to extract discriminative semantic features, which can dynamically calculate the attention weights to generate specific spatial attention kernels over different locations. Then, we combine the SAKGM with residual learning framework by embedding the SAKGM into a bottleneck residual block to obtain the residual spatial attention block (RSAB). The RSAKGN is constructed by stacking several RSABs. Experimental results on three public HSI datasets demonstrate that the proposed RSAKGN method outperforms several state-of-the-arts with small sample size." @default.
- W4285200322 created "2022-07-14" @default.
- W4285200322 creator A5000009227 @default.
- W4285200322 creator A5009501736 @default.
- W4285200322 creator A5026232217 @default.
- W4285200322 creator A5027632462 @default.
- W4285200322 creator A5086064008 @default.
- W4285200322 creator A5035394168 @default.
- W4285200322 date "2022-01-01" @default.
- W4285200322 modified "2023-10-16" @default.
- W4285200322 title "Residual Spatial Attention Kernel Generation Network for Hyperspectral Image Classification With Small Sample Size" @default.
- W4285200322 cites W1677182931 @default.
- W4285200322 cites W1997565609 @default.
- W4285200322 cites W2018257962 @default.
- W4285200322 cites W2029316659 @default.
- W4285200322 cites W2043665634 @default.
- W4285200322 cites W2087263574 @default.
- W4285200322 cites W2106277226 @default.
- W4285200322 cites W2113513024 @default.
- W4285200322 cites W2116699851 @default.
- W4285200322 cites W2127199143 @default.
- W4285200322 cites W2136251662 @default.
- W4285200322 cites W2165548826 @default.
- W4285200322 cites W2169500530 @default.
- W4285200322 cites W2194775991 @default.
- W4285200322 cites W2314785379 @default.
- W4285200322 cites W2500751094 @default.
- W4285200322 cites W2548791488 @default.
- W4285200322 cites W2572303978 @default.
- W4285200322 cites W2582369608 @default.
- W4285200322 cites W2719511702 @default.
- W4285200322 cites W2764276316 @default.
- W4285200322 cites W2767805377 @default.
- W4285200322 cites W2768537477 @default.
- W4285200322 cites W2792332881 @default.
- W4285200322 cites W2793645503 @default.
- W4285200322 cites W2799390666 @default.
- W4285200322 cites W2801324747 @default.
- W4285200322 cites W2822065499 @default.
- W4285200322 cites W2888119354 @default.
- W4285200322 cites W2890182766 @default.
- W4285200322 cites W2945768950 @default.
- W4285200322 cites W2971432438 @default.
- W4285200322 cites W2989871747 @default.
- W4285200322 cites W2993235622 @default.
- W4285200322 cites W3031696400 @default.
- W4285200322 cites W3034681889 @default.
- W4285200322 cites W3044657819 @default.
- W4285200322 cites W3047443805 @default.
- W4285200322 cites W3048631361 @default.
- W4285200322 cites W3104795559 @default.
- W4285200322 cites W3105357426 @default.
- W4285200322 cites W3148263657 @default.
- W4285200322 cites W3177349073 @default.
- W4285200322 cites W3191600511 @default.
- W4285200322 cites W3214821343 @default.
- W4285200322 doi "https://doi.org/10.1109/tgrs.2022.3175494" @default.
- W4285200322 hasPublicationYear "2022" @default.
- W4285200322 type Work @default.
- W4285200322 citedByCount "2" @default.
- W4285200322 countsByYear W42852003222022 @default.
- W4285200322 crossrefType "journal-article" @default.
- W4285200322 hasAuthorship W4285200322A5000009227 @default.
- W4285200322 hasAuthorship W4285200322A5009501736 @default.
- W4285200322 hasAuthorship W4285200322A5026232217 @default.
- W4285200322 hasAuthorship W4285200322A5027632462 @default.
- W4285200322 hasAuthorship W4285200322A5035394168 @default.
- W4285200322 hasAuthorship W4285200322A5086064008 @default.
- W4285200322 hasConcept C11413529 @default.
- W4285200322 hasConcept C114614502 @default.
- W4285200322 hasConcept C119857082 @default.
- W4285200322 hasConcept C153180895 @default.
- W4285200322 hasConcept C154945302 @default.
- W4285200322 hasConcept C155512373 @default.
- W4285200322 hasConcept C159078339 @default.
- W4285200322 hasConcept C2524010 @default.
- W4285200322 hasConcept C2777210771 @default.
- W4285200322 hasConcept C33923547 @default.
- W4285200322 hasConcept C41008148 @default.
- W4285200322 hasConcept C74193536 @default.
- W4285200322 hasConcept C81363708 @default.
- W4285200322 hasConcept C97931131 @default.
- W4285200322 hasConceptScore W4285200322C11413529 @default.
- W4285200322 hasConceptScore W4285200322C114614502 @default.
- W4285200322 hasConceptScore W4285200322C119857082 @default.
- W4285200322 hasConceptScore W4285200322C153180895 @default.
- W4285200322 hasConceptScore W4285200322C154945302 @default.
- W4285200322 hasConceptScore W4285200322C155512373 @default.
- W4285200322 hasConceptScore W4285200322C159078339 @default.
- W4285200322 hasConceptScore W4285200322C2524010 @default.
- W4285200322 hasConceptScore W4285200322C2777210771 @default.
- W4285200322 hasConceptScore W4285200322C33923547 @default.
- W4285200322 hasConceptScore W4285200322C41008148 @default.
- W4285200322 hasConceptScore W4285200322C74193536 @default.
- W4285200322 hasConceptScore W4285200322C81363708 @default.
- W4285200322 hasConceptScore W4285200322C97931131 @default.
- W4285200322 hasFunder F4320335777 @default.
- W4285200322 hasLocation W42852003221 @default.