Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285132110> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4285132110 endingPage "5" @default.
- W4285132110 startingPage "1" @default.
- W4285132110 abstract "Recently, graph convolutional network (GCN) has received more and more interest in the field of hyperspectral image classification (HSIC). The existing GCN-based models for HSIC propagate and aggregate information through the GCN network based on the graph, which is constructed according to spatial location or spectral similarity. However, the constructed graph may not be ideal for the downstream classification task due to the variety of spectral characteristics. In this paper, a fully connected graph is adaptively constructed to make full use of local spatial information and global spectral information. Besides, we apply a neural sparsification technique to remove potentially task-irrelevant edges in case of misleading message propagation. Furthermore, label propagation (LP) serves as regularization to assist the graph network in learning proper edge weights that lead to improved classification performance. The resulting network is end-to-end trainable. The experimental results on three popular benchmarks, including Indian Pines, Pavia University, and Kennedy Space Center, demonstrate the superiority of our algorithm." @default.
- W4285132110 created "2022-07-14" @default.
- W4285132110 creator A5035860485 @default.
- W4285132110 creator A5043672285 @default.
- W4285132110 creator A5053467438 @default.
- W4285132110 creator A5066300363 @default.
- W4285132110 creator A5079443694 @default.
- W4285132110 creator A5090470209 @default.
- W4285132110 creator A5091458655 @default.
- W4285132110 date "2022-01-01" @default.
- W4285132110 modified "2023-09-26" @default.
- W4285132110 title "Unifying Label Propagation and Graph Sparsification for Hyperspectral Image Classification" @default.
- W4285132110 cites W2043665634 @default.
- W4285132110 cites W2097092275 @default.
- W4285132110 cites W2131864940 @default.
- W4285132110 cites W2518815253 @default.
- W4285132110 cites W2572303978 @default.
- W4285132110 cites W2890022946 @default.
- W4285132110 cites W2892621946 @default.
- W4285132110 cites W2940678725 @default.
- W4285132110 cites W2966751049 @default.
- W4285132110 cites W2991494819 @default.
- W4285132110 cites W2994639710 @default.
- W4285132110 cites W3007536931 @default.
- W4285132110 cites W3024007459 @default.
- W4285132110 cites W3037458146 @default.
- W4285132110 cites W3043181422 @default.
- W4285132110 cites W3047443805 @default.
- W4285132110 cites W3048631361 @default.
- W4285132110 cites W3094570690 @default.
- W4285132110 cites W3107591966 @default.
- W4285132110 cites W3145049705 @default.
- W4285132110 cites W3157130577 @default.
- W4285132110 cites W3196410189 @default.
- W4285132110 cites W3202748052 @default.
- W4285132110 doi "https://doi.org/10.1109/lgrs.2022.3178708" @default.
- W4285132110 hasPublicationYear "2022" @default.
- W4285132110 type Work @default.
- W4285132110 citedByCount "3" @default.
- W4285132110 countsByYear W42851321102022 @default.
- W4285132110 countsByYear W42851321102023 @default.
- W4285132110 crossrefType "journal-article" @default.
- W4285132110 hasAuthorship W4285132110A5035860485 @default.
- W4285132110 hasAuthorship W4285132110A5043672285 @default.
- W4285132110 hasAuthorship W4285132110A5053467438 @default.
- W4285132110 hasAuthorship W4285132110A5066300363 @default.
- W4285132110 hasAuthorship W4285132110A5079443694 @default.
- W4285132110 hasAuthorship W4285132110A5090470209 @default.
- W4285132110 hasAuthorship W4285132110A5091458655 @default.
- W4285132110 hasConcept C132525143 @default.
- W4285132110 hasConcept C153180895 @default.
- W4285132110 hasConcept C154945302 @default.
- W4285132110 hasConcept C159078339 @default.
- W4285132110 hasConcept C2776135515 @default.
- W4285132110 hasConcept C41008148 @default.
- W4285132110 hasConcept C80444323 @default.
- W4285132110 hasConcept C81363708 @default.
- W4285132110 hasConceptScore W4285132110C132525143 @default.
- W4285132110 hasConceptScore W4285132110C153180895 @default.
- W4285132110 hasConceptScore W4285132110C154945302 @default.
- W4285132110 hasConceptScore W4285132110C159078339 @default.
- W4285132110 hasConceptScore W4285132110C2776135515 @default.
- W4285132110 hasConceptScore W4285132110C41008148 @default.
- W4285132110 hasConceptScore W4285132110C80444323 @default.
- W4285132110 hasConceptScore W4285132110C81363708 @default.
- W4285132110 hasLocation W42851321101 @default.
- W4285132110 hasOpenAccess W4285132110 @default.
- W4285132110 hasPrimaryLocation W42851321101 @default.
- W4285132110 hasRelatedWork W1869808405 @default.
- W4285132110 hasRelatedWork W2028628118 @default.
- W4285132110 hasRelatedWork W2781623059 @default.
- W4285132110 hasRelatedWork W2783789044 @default.
- W4285132110 hasRelatedWork W2807839383 @default.
- W4285132110 hasRelatedWork W3006465478 @default.
- W4285132110 hasRelatedWork W3093612317 @default.
- W4285132110 hasRelatedWork W3173596272 @default.
- W4285132110 hasRelatedWork W3211035526 @default.
- W4285132110 hasRelatedWork W4291701050 @default.
- W4285132110 hasVolume "19" @default.
- W4285132110 isParatext "false" @default.
- W4285132110 isRetracted "false" @default.
- W4285132110 workType "article" @default.