Matches in SemOpenAlex for { <https://semopenalex.org/work/W2975089237> ?p ?o ?g. }
- W2975089237 abstract "In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed Graph Convolutional Network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2D image grids. Second, we refine the graph edge weight and the connective relationships among image regions by learning the improved adjacency matrix and the 'edge filter', so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in accurate region representations, and vice versa. The experiments carried out on three real-world benchmark datasets demonstrate that the proposed method yields significant improvement in the classification performance when compared with some state-of-the-art approaches." @default.
- W2975089237 created "2019-10-03" @default.
- W2975089237 creator A5008056593 @default.
- W2975089237 creator A5018712863 @default.
- W2975089237 creator A5030222911 @default.
- W2975089237 creator A5058747937 @default.
- W2975089237 creator A5062318228 @default.
- W2975089237 creator A5079556851 @default.
- W2975089237 date "2019-09-26" @default.
- W2975089237 modified "2023-09-25" @default.
- W2975089237 title "Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network" @default.
- W2975089237 cites W1588948804 @default.
- W2975089237 cites W1590946397 @default.
- W2975089237 cites W1662382123 @default.
- W2975089237 cites W1667249920 @default.
- W2975089237 cites W1939429412 @default.
- W2975089237 cites W1975981790 @default.
- W2975089237 cites W2001298023 @default.
- W2975089237 cites W2001914975 @default.
- W2975089237 cites W2003684104 @default.
- W2975089237 cites W2004754531 @default.
- W2975089237 cites W2031510368 @default.
- W2975089237 cites W2041100636 @default.
- W2975089237 cites W2043665634 @default.
- W2975089237 cites W2046253692 @default.
- W2975089237 cites W2049444988 @default.
- W2975089237 cites W2064604707 @default.
- W2975089237 cites W2097915756 @default.
- W2975089237 cites W2103094532 @default.
- W2975089237 cites W2113513024 @default.
- W2975089237 cites W2114819256 @default.
- W2975089237 cites W2115451191 @default.
- W2975089237 cites W2117741752 @default.
- W2975089237 cites W2118246710 @default.
- W2975089237 cites W2124571274 @default.
- W2975089237 cites W2127199143 @default.
- W2975089237 cites W2136251662 @default.
- W2975089237 cites W2143340118 @default.
- W2975089237 cites W2144966944 @default.
- W2975089237 cites W2154636369 @default.
- W2975089237 cites W2154874087 @default.
- W2975089237 cites W2155658307 @default.
- W2975089237 cites W2158787690 @default.
- W2975089237 cites W2159070926 @default.
- W2975089237 cites W2164330327 @default.
- W2975089237 cites W2168880067 @default.
- W2975089237 cites W2249375231 @default.
- W2975089237 cites W2518815253 @default.
- W2975089237 cites W2548791488 @default.
- W2975089237 cites W2556967412 @default.
- W2975089237 cites W2563100679 @default.
- W2975089237 cites W2624431344 @default.
- W2975089237 cites W2756289082 @default.
- W2975089237 cites W2766453196 @default.
- W2975089237 cites W2767805377 @default.
- W2975089237 cites W2770201307 @default.
- W2975089237 cites W2789643644 @default.
- W2975089237 cites W2792083654 @default.
- W2975089237 cites W2799390666 @default.
- W2975089237 cites W2890779863 @default.
- W2975089237 cites W2892621946 @default.
- W2975089237 cites W2962767366 @default.
- W2975089237 cites W2963017945 @default.
- W2975089237 cites W2964015378 @default.
- W2975089237 cites W2964321699 @default.
- W2975089237 cites W3100848837 @default.
- W2975089237 cites W3104795559 @default.
- W2975089237 doi "https://doi.org/10.48550/arxiv.1909.11953" @default.
- W2975089237 hasPublicationYear "2019" @default.
- W2975089237 type Work @default.
- W2975089237 sameAs 2975089237 @default.
- W2975089237 citedByCount "0" @default.
- W2975089237 crossrefType "posted-content" @default.
- W2975089237 hasAuthorship W2975089237A5008056593 @default.
- W2975089237 hasAuthorship W2975089237A5018712863 @default.
- W2975089237 hasAuthorship W2975089237A5030222911 @default.
- W2975089237 hasAuthorship W2975089237A5058747937 @default.
- W2975089237 hasAuthorship W2975089237A5062318228 @default.
- W2975089237 hasAuthorship W2975089237A5079556851 @default.
- W2975089237 hasBestOaLocation W29750892371 @default.
- W2975089237 hasConcept C110484373 @default.
- W2975089237 hasConcept C11413529 @default.
- W2975089237 hasConcept C132525143 @default.
- W2975089237 hasConcept C153180895 @default.
- W2975089237 hasConcept C154945302 @default.
- W2975089237 hasConcept C159078339 @default.
- W2975089237 hasConcept C160633673 @default.
- W2975089237 hasConcept C165696696 @default.
- W2975089237 hasConcept C180356752 @default.
- W2975089237 hasConcept C38652104 @default.
- W2975089237 hasConcept C41008148 @default.
- W2975089237 hasConcept C64754055 @default.
- W2975089237 hasConcept C80444323 @default.
- W2975089237 hasConceptScore W2975089237C110484373 @default.
- W2975089237 hasConceptScore W2975089237C11413529 @default.
- W2975089237 hasConceptScore W2975089237C132525143 @default.
- W2975089237 hasConceptScore W2975089237C153180895 @default.
- W2975089237 hasConceptScore W2975089237C154945302 @default.
- W2975089237 hasConceptScore W2975089237C159078339 @default.
- W2975089237 hasConceptScore W2975089237C160633673 @default.