Matches in SemOpenAlex for { <https://semopenalex.org/work/W2976262783> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2976262783 abstract "Although complex-valued (CV) neural networks have shown better classification results compared to their real-valued (RV) counterparts for polarimetric synthetic aperture radar (PolSAR) classification, the extension of pixel-level RV networks to the complex domain has not yet thoroughly examined. This paper presents a novel complex-valued deep fully convolutional neural network (CV-FCN) designed for PolSAR image classification. Specifically, CV-FCN uses PolSAR CV data that includes the phase information and utilizes the deep FCN architecture that performs pixel-level labeling. It integrates the feature extraction module and the classification module in a united framework. Technically, for the particularity of PolSAR data, a dedicated complex-valued weight initialization scheme is defined to initialize CV-FCN. It considers the distribution of polarization data to conduct CV-FCN training from scratch in an efficient and fast manner. CV-FCN employs a complex downsampling-then-upsampling scheme to extract dense features. To enrich discriminative information, multi-level CV features that retain more polarization information are extracted via the complex downsampling scheme. Then, a complex upsampling scheme is proposed to predict dense CV labeling. It employs complex max-unpooling layers to greatly capture more spatial information for better robustness to speckle noise. In addition, to achieve faster convergence and obtain more precise classification results, a novel average cross-entropy loss function is derived for CV-FCN optimization. Experiments on real PolSAR datasets demonstrate that CV-FCN achieves better classification performance than other state-of-art methods." @default.
- W2976262783 created "2019-10-03" @default.
- W2976262783 creator A5010555402 @default.
- W2976262783 creator A5015652605 @default.
- W2976262783 creator A5019152413 @default.
- W2976262783 creator A5029360035 @default.
- W2976262783 creator A5087038469 @default.
- W2976262783 date "2019-09-29" @default.
- W2976262783 modified "2023-10-18" @default.
- W2976262783 title "Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network" @default.
- W2976262783 cites W1677182931 @default.
- W2976262783 cites W1849277567 @default.
- W2976262783 cites W1903029394 @default.
- W2976262783 cites W1974024703 @default.
- W2976262783 cites W1989757000 @default.
- W2976262783 cites W1992824785 @default.
- W2976262783 cites W2008826820 @default.
- W2976262783 cites W2030728252 @default.
- W2976262783 cites W2048578702 @default.
- W2976262783 cites W2077547750 @default.
- W2976262783 cites W2078985447 @default.
- W2976262783 cites W2081144903 @default.
- W2976262783 cites W2101690226 @default.
- W2976262783 cites W2105923215 @default.
- W2976262783 cites W2114578114 @default.
- W2976262783 cites W2132012856 @default.
- W2976262783 cites W2133989913 @default.
- W2976262783 cites W2144554203 @default.
- W2976262783 cites W2170481611 @default.
- W2976262783 cites W2345055757 @default.
- W2976262783 cites W2574739416 @default.
- W2976262783 cites W2593886839 @default.
- W2976262783 cites W2616755213 @default.
- W2976262783 cites W2618946976 @default.
- W2976262783 cites W2754361766 @default.
- W2976262783 cites W2766299269 @default.
- W2976262783 cites W2767003110 @default.
- W2976262783 cites W2770727026 @default.
- W2976262783 cites W2772082715 @default.
- W2976262783 cites W2782522152 @default.
- W2976262783 cites W2789584428 @default.
- W2976262783 cites W2793268137 @default.
- W2976262783 cites W2804230435 @default.
- W2976262783 cites W2804850629 @default.
- W2976262783 cites W2897760800 @default.
- W2976262783 cites W2904891876 @default.
- W2976262783 cites W3105127913 @default.
- W2976262783 cites W3020984796 @default.
- W2976262783 doi "https://doi.org/10.48550/arxiv.1909.13299" @default.
- W2976262783 hasPublicationYear "2019" @default.
- W2976262783 type Work @default.
- W2976262783 sameAs 2976262783 @default.
- W2976262783 citedByCount "0" @default.
- W2976262783 crossrefType "posted-content" @default.
- W2976262783 hasAuthorship W2976262783A5010555402 @default.
- W2976262783 hasAuthorship W2976262783A5015652605 @default.
- W2976262783 hasAuthorship W2976262783A5019152413 @default.
- W2976262783 hasAuthorship W2976262783A5029360035 @default.
- W2976262783 hasAuthorship W2976262783A5087038469 @default.
- W2976262783 hasBestOaLocation W29762627831 @default.
- W2976262783 hasConcept C110384440 @default.
- W2976262783 hasConcept C114466953 @default.
- W2976262783 hasConcept C115961682 @default.
- W2976262783 hasConcept C153180895 @default.
- W2976262783 hasConcept C154945302 @default.
- W2976262783 hasConcept C160633673 @default.
- W2976262783 hasConcept C199360897 @default.
- W2976262783 hasConcept C41008148 @default.
- W2976262783 hasConcept C75294576 @default.
- W2976262783 hasConcept C81363708 @default.
- W2976262783 hasConcept C97931131 @default.
- W2976262783 hasConceptScore W2976262783C110384440 @default.
- W2976262783 hasConceptScore W2976262783C114466953 @default.
- W2976262783 hasConceptScore W2976262783C115961682 @default.
- W2976262783 hasConceptScore W2976262783C153180895 @default.
- W2976262783 hasConceptScore W2976262783C154945302 @default.
- W2976262783 hasConceptScore W2976262783C160633673 @default.
- W2976262783 hasConceptScore W2976262783C199360897 @default.
- W2976262783 hasConceptScore W2976262783C41008148 @default.
- W2976262783 hasConceptScore W2976262783C75294576 @default.
- W2976262783 hasConceptScore W2976262783C81363708 @default.
- W2976262783 hasConceptScore W2976262783C97931131 @default.
- W2976262783 hasLocation W29762627831 @default.
- W2976262783 hasOpenAccess W2976262783 @default.
- W2976262783 hasPrimaryLocation W29762627831 @default.
- W2976262783 hasRelatedWork W1914651075 @default.
- W2976262783 hasRelatedWork W1982774199 @default.
- W2976262783 hasRelatedWork W2026121273 @default.
- W2976262783 hasRelatedWork W2136485282 @default.
- W2976262783 hasRelatedWork W2406522397 @default.
- W2976262783 hasRelatedWork W2518599539 @default.
- W2976262783 hasRelatedWork W2546871836 @default.
- W2976262783 hasRelatedWork W2726121760 @default.
- W2976262783 hasRelatedWork W2773500201 @default.
- W2976262783 hasRelatedWork W4319301798 @default.
- W2976262783 isParatext "false" @default.
- W2976262783 isRetracted "false" @default.
- W2976262783 magId "2976262783" @default.
- W2976262783 workType "article" @default.