Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386077592> ?p ?o ?g. }
- W4386077592 endingPage "15" @default.
- W4386077592 startingPage "1" @default.
- W4386077592 abstract "Graph convolutional network (GCN) has recently received increasing attention in hyperspectral image (HSI) classification, benefiting from its superiority in conducting shape adaptive convolutions on arbitrary non-Euclidean structure data. However, the performance of GCN heavily depends on the quality of the initial graph. Conventional GCN-based methods only adopt spectral-spatial similarity to build the initial graph without extracting other contextual information from neighboring nodes. In addition, most GCN-based methods use shallow layers, which cannot extract deep discriminative features from HSIs under the limited number of training samples. To solve these issues, we propose a superpixel feature learning via offset graph U-Net for HSI classification, which can learn deep discriminative features from HSIs. Multiple strategies of measuring similarity among superpixels are utilized to build the initial graph, including spectral information, spatial information and context-aware information among nodes, making the initial graph more accurate. Furthermore, the graph U-Net structure, containing the graph pooling layer and the graph unpooling layer, is helpful in constructing deep GCN layers and learning multi-scale features, which can alleviate the oversmoothing problem. Moreover, an offset module is introduced to emphasize the local spectral-spatial information. Finally, we comprehensively evaluate the proposed method on three public data sets. The experimental results demonstrate the superiority of the proposed approach compared with other state-of-the-art methods." @default.
- W4386077592 created "2023-08-23" @default.
- W4386077592 creator A5028229932 @default.
- W4386077592 creator A5035508615 @default.
- W4386077592 creator A5038432832 @default.
- W4386077592 creator A5043777501 @default.
- W4386077592 creator A5048207713 @default.
- W4386077592 date "2023-01-01" @default.
- W4386077592 modified "2023-10-16" @default.
- W4386077592 title "An Offset Graph U-Net for Hyperspectral Image Classification" @default.
- W4386077592 cites W1522547150 @default.
- W4386077592 cites W1939429412 @default.
- W4386077592 cites W1964541653 @default.
- W4386077592 cites W1966580635 @default.
- W4386077592 cites W1988386267 @default.
- W4386077592 cites W1990895816 @default.
- W4386077592 cites W2043665634 @default.
- W4386077592 cites W2097092275 @default.
- W4386077592 cites W2097915756 @default.
- W4386077592 cites W2118246710 @default.
- W4386077592 cites W2158787690 @default.
- W4386077592 cites W2194775991 @default.
- W4386077592 cites W2412782625 @default.
- W4386077592 cites W2500751094 @default.
- W4386077592 cites W2548791488 @default.
- W4386077592 cites W2572303978 @default.
- W4386077592 cites W2764276316 @default.
- W4386077592 cites W2767805377 @default.
- W4386077592 cites W2777427437 @default.
- W4386077592 cites W2791006446 @default.
- W4386077592 cites W2852622981 @default.
- W4386077592 cites W2892621946 @default.
- W4386077592 cites W2898381489 @default.
- W4386077592 cites W2942170965 @default.
- W4386077592 cites W2962949934 @default.
- W4386077592 cites W2963446712 @default.
- W4386077592 cites W2991494819 @default.
- W4386077592 cites W2992919850 @default.
- W4386077592 cites W3024007459 @default.
- W4386077592 cites W3028306149 @default.
- W4386077592 cites W3047443805 @default.
- W4386077592 cites W3092916389 @default.
- W4386077592 cites W3094570690 @default.
- W4386077592 cites W3101640299 @default.
- W4386077592 cites W3105357426 @default.
- W4386077592 cites W3107591966 @default.
- W4386077592 cites W3114720220 @default.
- W4386077592 cites W3146366485 @default.
- W4386077592 cites W3154322353 @default.
- W4386077592 cites W3189222621 @default.
- W4386077592 cites W3200705513 @default.
- W4386077592 cites W3202748052 @default.
- W4386077592 cites W3205965083 @default.
- W4386077592 cites W3208943037 @default.
- W4386077592 cites W4205349001 @default.
- W4386077592 cites W4206104510 @default.
- W4386077592 cites W4210628037 @default.
- W4386077592 cites W4210794570 @default.
- W4386077592 cites W4214711995 @default.
- W4386077592 cites W4220777959 @default.
- W4386077592 cites W4226467560 @default.
- W4386077592 cites W4240485910 @default.
- W4386077592 cites W4285180452 @default.
- W4386077592 cites W4293733592 @default.
- W4386077592 cites W4319069095 @default.
- W4386077592 cites W4323338598 @default.
- W4386077592 cites W4327521838 @default.
- W4386077592 cites W4367320924 @default.
- W4386077592 cites W4378082492 @default.
- W4386077592 doi "https://doi.org/10.1109/tgrs.2023.3307609" @default.
- W4386077592 hasPublicationYear "2023" @default.
- W4386077592 type Work @default.
- W4386077592 citedByCount "0" @default.
- W4386077592 crossrefType "journal-article" @default.
- W4386077592 hasAuthorship W4386077592A5028229932 @default.
- W4386077592 hasAuthorship W4386077592A5035508615 @default.
- W4386077592 hasAuthorship W4386077592A5038432832 @default.
- W4386077592 hasAuthorship W4386077592A5043777501 @default.
- W4386077592 hasAuthorship W4386077592A5048207713 @default.
- W4386077592 hasConcept C132525143 @default.
- W4386077592 hasConcept C153180895 @default.
- W4386077592 hasConcept C154945302 @default.
- W4386077592 hasConcept C159078339 @default.
- W4386077592 hasConcept C175291020 @default.
- W4386077592 hasConcept C199360897 @default.
- W4386077592 hasConcept C41008148 @default.
- W4386077592 hasConcept C70437156 @default.
- W4386077592 hasConcept C80444323 @default.
- W4386077592 hasConcept C97931131 @default.
- W4386077592 hasConceptScore W4386077592C132525143 @default.
- W4386077592 hasConceptScore W4386077592C153180895 @default.
- W4386077592 hasConceptScore W4386077592C154945302 @default.
- W4386077592 hasConceptScore W4386077592C159078339 @default.
- W4386077592 hasConceptScore W4386077592C175291020 @default.
- W4386077592 hasConceptScore W4386077592C199360897 @default.
- W4386077592 hasConceptScore W4386077592C41008148 @default.
- W4386077592 hasConceptScore W4386077592C70437156 @default.
- W4386077592 hasConceptScore W4386077592C80444323 @default.