FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945336884> ?p ?o ?g. }

• W2945336884 endingPage "1116" @default.
• W2945336884 startingPage "1116" @default.
• W2945336884 abstract "In a real hyperspectral image classification task, label noise inevitably exists in training samples. To deal with label noise, current methods assume that noise obeys the Gaussian distribution, which is not the real case in practice, because in most cases, we are more likely to misclassify training samples at the boundaries between different classes. In this paper, we propose a spectral–spatial sparse graph-based adaptive label propagation (SALP) algorithm to address a more practical case, where the label information is contaminated by random noise and boundary noise. Specifically, the SALP mainly includes two steps: First, a spectral–spatial sparse graph is constructed to depict the contextual correlations between pixels within the same superpixel homogeneous region, which are generated by superpixel image segmentation, and then a transfer matrix is produced to describe the transition probability between pixels. Second, after randomly splitting training pixels into “clean” and “polluted,” we iteratively propagate the label information from “clean” to “polluted” based on the transfer matrix, and the relabeling strategy for each pixel is adaptively adjusted along with its spatial position in the corresponding homogeneous region. Experimental results on two standard hyperspectral image datasets show that the proposed SALP over four major classifiers can significantly decrease the influence of noisy labels, and our method achieves better performance compared with the baselines." @default.
• W2945336884 created "2019-05-29" @default.
• W2945336884 creator A5015552513 @default.
• W2945336884 creator A5031746055 @default.
• W2945336884 creator A5087165831 @default.
• W2945336884 date "2019-05-10" @default.
• W2945336884 modified "2023-09-26" @default.
• W2945336884 title "Label Noise Cleansing with Sparse Graph for Hyperspectral Image Classification" @default.
• W2945336884 cites W1514928307 @default.
• W2945336884 cites W1517907761 @default.
• W2945336884 cites W1897878572 @default.
• W2945336884 cites W1904464160 @default.
• W2945336884 cites W1964315230 @default.
• W2945336884 cites W1972524915 @default.
• W2945336884 cites W1995443851 @default.
• W2945336884 cites W2002849025 @default.
• W2945336884 cites W2008847349 @default.
• W2945336884 cites W2031596661 @default.
• W2945336884 cites W2049444988 @default.
• W2945336884 cites W2050834445 @default.
• W2945336884 cites W2059110141 @default.
• W2945336884 cites W2070534370 @default.
• W2945336884 cites W2074506978 @default.
• W2945336884 cites W2089468765 @default.
• W2945336884 cites W2096553553 @default.
• W2945336884 cites W2097915756 @default.
• W2945336884 cites W2098933520 @default.
• W2945336884 cites W2105386417 @default.
• W2945336884 cites W2122287830 @default.
• W2945336884 cites W2136251662 @default.
• W2945336884 cites W2152057649 @default.
• W2945336884 cites W2166923144 @default.
• W2945336884 cites W2167460663 @default.
• W2945336884 cites W2298855392 @default.
• W2945336884 cites W2307231389 @default.
• W2945336884 cites W2342432966 @default.
• W2945336884 cites W2520742745 @default.
• W2945336884 cites W2577727229 @default.
• W2945336884 cites W2586793539 @default.
• W2945336884 cites W2589453516 @default.
• W2945336884 cites W2591248827 @default.
• W2945336884 cites W2603834682 @default.
• W2945336884 cites W2719511702 @default.
• W2945336884 cites W2729550389 @default.
• W2945336884 cites W2740578684 @default.
• W2945336884 cites W2767805377 @default.
• W2945336884 cites W2791006446 @default.
• W2945336884 cites W2799870441 @default.
• W2945336884 cites W2801018674 @default.
• W2945336884 cites W2803177391 @default.
• W2945336884 cites W2809635958 @default.
• W2945336884 cites W2890022946 @default.
• W2945336884 cites W2897194080 @default.
• W2945336884 cites W2898532184 @default.
• W2945336884 cites W2906616692 @default.
• W2945336884 cites W2912147220 @default.
• W2945336884 cites W3100499011 @default.
• W2945336884 cites W3106239502 @default.
• W2945336884 cites W4244259635 @default.
• W2945336884 cites W4288076010 @default.
• W2945336884 doi "https://doi.org/10.3390/rs11091116" @default.
• W2945336884 hasPublicationYear "2019" @default.
• W2945336884 type Work @default.
• W2945336884 sameAs 2945336884 @default.
• W2945336884 citedByCount "12" @default.
• W2945336884 countsByYear W29453368842020 @default.
• W2945336884 countsByYear W29453368842021 @default.
• W2945336884 countsByYear W29453368842022 @default.
• W2945336884 countsByYear W29453368842023 @default.
• W2945336884 crossrefType "journal-article" @default.
• W2945336884 hasAuthorship W2945336884A5015552513 @default.
• W2945336884 hasAuthorship W2945336884A5031746055 @default.
• W2945336884 hasAuthorship W2945336884A5087165831 @default.
• W2945336884 hasBestOaLocation W29453368841 @default.
• W2945336884 hasConcept C102192266 @default.
• W2945336884 hasConcept C105795698 @default.
• W2945336884 hasConcept C115961682 @default.
• W2945336884 hasConcept C121332964 @default.
• W2945336884 hasConcept C124066611 @default.
• W2945336884 hasConcept C124504099 @default.
• W2945336884 hasConcept C13251829 @default.
• W2945336884 hasConcept C132525143 @default.
• W2945336884 hasConcept C153180895 @default.
• W2945336884 hasConcept C154945302 @default.
• W2945336884 hasConcept C159078339 @default.
• W2945336884 hasConcept C159620131 @default.
• W2945336884 hasConcept C160633673 @default.
• W2945336884 hasConcept C163716315 @default.
• W2945336884 hasConcept C203776342 @default.
• W2945336884 hasConcept C31972630 @default.
• W2945336884 hasConcept C33923547 @default.
• W2945336884 hasConcept C41008148 @default.
• W2945336884 hasConcept C4199805 @default.
• W2945336884 hasConcept C5134670 @default.
• W2945336884 hasConcept C56372850 @default.
• W2945336884 hasConcept C62520636 @default.
• W2945336884 hasConcept C80444323 @default.
• W2945336884 hasConcept C89600930 @default.

• next