FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128144003> ?p ?o ?g. }

• W3128144003 abstract "Linear Mixture Model for hyperspectral datasets involves separating a mixed pixel as a linear combination of its constituent endmembers and corresponding fractional abundances. Both optimization and neural methods have attempted to tackle this problem, with the current state of the art results achieved by neural models on benchmark datasets. However, our review of these neural models show that these networks are severely over-parameterized and consequently the invariant endmember spectra extracted as decoder weights has a high variance over multiple runs. All of these approaches require substantial post-processing to satisfy LMM constraints. Furthermore, they also require an exact specification of the number of endmembers and specialized initialization of weights from other algorithms like VCA. Our work shows for the first time that a two-layer autoencoder (SCA-Net), with $2FK$ parameters ($F$ features, $K$ endmembers), achieves error metrics that are scales apart ($10^{-5})$ from previously reported values $(10^{-2})$. SCA-Net converges to this low error solution starting from a random initialization of weights. We also show that SCA-Net, based upon a bi-orthogonal representation, performs a self-correction when the the number of endmembers are over-specified. We show that our network formulation extracts a low-rank representation that is bounded below by a tail-energy and can be computationally verified. Our numerical experiments on Samson, Jasper, and Urban datasets demonstrate that SCA-Net outperforms previously reported error metrics for all the cases while being robust to noise and outliers." @default.
• W3128144003 created "2021-02-15" @default.
• W3128144003 creator A5016634390 @default.
• W3128144003 creator A5019155832 @default.
• W3128144003 creator A5023397430 @default.
• W3128144003 creator A5089253713 @default.
• W3128144003 date "2021-02-10" @default.
• W3128144003 modified "2023-09-27" @default.
• W3128144003 title "SCA-Net: A Self-Correcting Two-Layer Autoencoder for Hyper-spectral Unmixing." @default.
• W3128144003 cites W1522301498 @default.
• W3128144003 cites W1582058549 @default.
• W3128144003 cites W2004026774 @default.
• W3128144003 cites W2009576740 @default.
• W3128144003 cites W2017089497 @default.
• W3128144003 cites W2042737021 @default.
• W3128144003 cites W2044496796 @default.
• W3128144003 cites W2050041778 @default.
• W3128144003 cites W2087263574 @default.
• W3128144003 cites W2098295833 @default.
• W3128144003 cites W2101837437 @default.
• W3128144003 cites W2108119513 @default.
• W3128144003 cites W2114486983 @default.
• W3128144003 cites W2117027921 @default.
• W3128144003 cites W2122976738 @default.
• W3128144003 cites W2127062304 @default.
• W3128144003 cites W2134328014 @default.
• W3128144003 cites W2146130404 @default.
• W3128144003 cites W2156458885 @default.
• W3128144003 cites W2157321686 @default.
• W3128144003 cites W2165755981 @default.
• W3128144003 cites W2774517539 @default.
• W3128144003 cites W2911419410 @default.
• W3128144003 cites W2963371848 @default.
• W3128144003 cites W2968732335 @default.
• W3128144003 cites W3005148902 @default.
• W3128144003 cites W3029645440 @default.
• W3128144003 cites W3122463936 @default.
• W3128144003 cites W3138729301 @default.
• W3128144003 cites W3139499394 @default.
• W3128144003 hasPublicationYear "2021" @default.
• W3128144003 type Work @default.
• W3128144003 sameAs 3128144003 @default.
• W3128144003 citedByCount "0" @default.
• W3128144003 crossrefType "posted-content" @default.
• W3128144003 hasAuthorship W3128144003A5016634390 @default.
• W3128144003 hasAuthorship W3128144003A5019155832 @default.
• W3128144003 hasAuthorship W3128144003A5023397430 @default.
• W3128144003 hasAuthorship W3128144003A5089253713 @default.
• W3128144003 hasConcept C101738243 @default.
• W3128144003 hasConcept C11413529 @default.
• W3128144003 hasConcept C114466953 @default.
• W3128144003 hasConcept C13280743 @default.
• W3128144003 hasConcept C153180895 @default.
• W3128144003 hasConcept C154945302 @default.
• W3128144003 hasConcept C159078339 @default.
• W3128144003 hasConcept C165464430 @default.
• W3128144003 hasConcept C185798385 @default.
• W3128144003 hasConcept C199360897 @default.
• W3128144003 hasConcept C205649164 @default.
• W3128144003 hasConcept C33923547 @default.
• W3128144003 hasConcept C41008148 @default.
• W3128144003 hasConcept C50644808 @default.
• W3128144003 hasConcept C58237817 @default.
• W3128144003 hasConcept C79337645 @default.
• W3128144003 hasConceptScore W3128144003C101738243 @default.
• W3128144003 hasConceptScore W3128144003C11413529 @default.
• W3128144003 hasConceptScore W3128144003C114466953 @default.
• W3128144003 hasConceptScore W3128144003C13280743 @default.
• W3128144003 hasConceptScore W3128144003C153180895 @default.
• W3128144003 hasConceptScore W3128144003C154945302 @default.
• W3128144003 hasConceptScore W3128144003C159078339 @default.
• W3128144003 hasConceptScore W3128144003C165464430 @default.
• W3128144003 hasConceptScore W3128144003C185798385 @default.
• W3128144003 hasConceptScore W3128144003C199360897 @default.
• W3128144003 hasConceptScore W3128144003C205649164 @default.
• W3128144003 hasConceptScore W3128144003C33923547 @default.
• W3128144003 hasConceptScore W3128144003C41008148 @default.
• W3128144003 hasConceptScore W3128144003C50644808 @default.
• W3128144003 hasConceptScore W3128144003C58237817 @default.
• W3128144003 hasConceptScore W3128144003C79337645 @default.
• W3128144003 hasLocation W31281440031 @default.
• W3128144003 hasOpenAccess W3128144003 @default.
• W3128144003 hasPrimaryLocation W31281440031 @default.
• W3128144003 hasRelatedWork W1993758285 @default.
• W3128144003 hasRelatedWork W2018081610 @default.
• W3128144003 hasRelatedWork W2034371392 @default.
• W3128144003 hasRelatedWork W2055596845 @default.
• W3128144003 hasRelatedWork W2103581346 @default.
• W3128144003 hasRelatedWork W2104650092 @default.
• W3128144003 hasRelatedWork W2231243630 @default.
• W3128144003 hasRelatedWork W2587801071 @default.
• W3128144003 hasRelatedWork W2589865066 @default.
• W3128144003 hasRelatedWork W2618410756 @default.
• W3128144003 hasRelatedWork W2740196585 @default.
• W3128144003 hasRelatedWork W2921234600 @default.
• W3128144003 hasRelatedWork W2952506132 @default.
• W3128144003 hasRelatedWork W2953121441 @default.
• W3128144003 hasRelatedWork W2979854415 @default.
• W3128144003 hasRelatedWork W3034868650 @default.
• W3128144003 hasRelatedWork W3089060219 @default.

• next