Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293731510> ?p ?o ?g. }
- W4293731510 endingPage "15" @default.
- W4293731510 startingPage "1" @default.
- W4293731510 abstract "Deep learning (DL) methods usually need to collect a large amount of labeled data to extract deep features. However, due to the difficulty of obtaining numerous labeled data from synthetic aperture radar (SAR) images, unsupervised feature learning has been focused on SAR image processing. In this paper, we propose a three-dimensional sparse model (3-DSM) to extract deep sparse features from SAR images in an unsupervised way. Concretely, 3-DSM learns the convolution kernels by minimizing the error between the features and the constructed sparse maps, without labeled samples. Thus, the discriminative features can be extracted in an unsupervised way by the learned convolution kernels and are able to capture the main structure information of SAR images. Furthermore, to the best of our knowledge, 3-DSM firstly specifies the sparsity of convolution kernels, with each convolution kernel exhibiting its independence from the others and the redundancy of convolution kernels being diminishing. It means that each convolution kernel extracts its unique structural features of SAR images. Consequently, in the feature extraction, three-dimensional sparsities have been specified, including width, height, and depth, with the acquisition of discriminative less-redundant features. The effectiveness of 3-DSM is demonstrated by the feature extraction and segmentation of the simulated and real SAR images." @default.
- W4293731510 created "2022-08-31" @default.
- W4293731510 creator A5010639562 @default.
- W4293731510 creator A5082599988 @default.
- W4293731510 creator A5084667178 @default.
- W4293731510 creator A5088683171 @default.
- W4293731510 date "2022-01-01" @default.
- W4293731510 modified "2023-10-14" @default.
- W4293731510 title "Unsupervised Deep Sparse Features Extraction for SAR Image Segmentation" @default.
- W4293731510 cites W1696305814 @default.
- W4293731510 cites W1904499812 @default.
- W4293731510 cites W1964803612 @default.
- W4293731510 cites W1967810897 @default.
- W4293731510 cites W1972281563 @default.
- W4293731510 cites W2019779527 @default.
- W4293731510 cites W2032786999 @default.
- W4293731510 cites W2046005667 @default.
- W4293731510 cites W2100495367 @default.
- W4293731510 cites W2144554203 @default.
- W4293731510 cites W2146123543 @default.
- W4293731510 cites W2153635508 @default.
- W4293731510 cites W2158242013 @default.
- W4293731510 cites W2168239404 @default.
- W4293731510 cites W2179290474 @default.
- W4293731510 cites W2293077323 @default.
- W4293731510 cites W2293779343 @default.
- W4293731510 cites W2340896621 @default.
- W4293731510 cites W2401650711 @default.
- W4293731510 cites W2772137563 @default.
- W4293731510 cites W2774858324 @default.
- W4293731510 cites W2792706032 @default.
- W4293731510 cites W2814869128 @default.
- W4293731510 cites W2900131614 @default.
- W4293731510 cites W2907100627 @default.
- W4293731510 cites W3003598450 @default.
- W4293731510 cites W3004953122 @default.
- W4293731510 cites W3006462480 @default.
- W4293731510 cites W3015363211 @default.
- W4293731510 cites W3026889349 @default.
- W4293731510 cites W3035559754 @default.
- W4293731510 cites W3038113894 @default.
- W4293731510 cites W3088975408 @default.
- W4293731510 cites W3103868052 @default.
- W4293731510 cites W3156910157 @default.
- W4293731510 cites W3159815144 @default.
- W4293731510 cites W4220953084 @default.
- W4293731510 cites W66352275 @default.
- W4293731510 doi "https://doi.org/10.1109/tgrs.2022.3202701" @default.
- W4293731510 hasPublicationYear "2022" @default.
- W4293731510 type Work @default.
- W4293731510 citedByCount "1" @default.
- W4293731510 crossrefType "journal-article" @default.
- W4293731510 hasAuthorship W4293731510A5010639562 @default.
- W4293731510 hasAuthorship W4293731510A5082599988 @default.
- W4293731510 hasAuthorship W4293731510A5084667178 @default.
- W4293731510 hasAuthorship W4293731510A5088683171 @default.
- W4293731510 hasConcept C111919701 @default.
- W4293731510 hasConcept C114614502 @default.
- W4293731510 hasConcept C152124472 @default.
- W4293731510 hasConcept C153180895 @default.
- W4293731510 hasConcept C154945302 @default.
- W4293731510 hasConcept C31972630 @default.
- W4293731510 hasConcept C33923547 @default.
- W4293731510 hasConcept C41008148 @default.
- W4293731510 hasConcept C45347329 @default.
- W4293731510 hasConcept C50644808 @default.
- W4293731510 hasConcept C52622490 @default.
- W4293731510 hasConcept C74193536 @default.
- W4293731510 hasConcept C87360688 @default.
- W4293731510 hasConcept C89600930 @default.
- W4293731510 hasConcept C97931131 @default.
- W4293731510 hasConceptScore W4293731510C111919701 @default.
- W4293731510 hasConceptScore W4293731510C114614502 @default.
- W4293731510 hasConceptScore W4293731510C152124472 @default.
- W4293731510 hasConceptScore W4293731510C153180895 @default.
- W4293731510 hasConceptScore W4293731510C154945302 @default.
- W4293731510 hasConceptScore W4293731510C31972630 @default.
- W4293731510 hasConceptScore W4293731510C33923547 @default.
- W4293731510 hasConceptScore W4293731510C41008148 @default.
- W4293731510 hasConceptScore W4293731510C45347329 @default.
- W4293731510 hasConceptScore W4293731510C50644808 @default.
- W4293731510 hasConceptScore W4293731510C52622490 @default.
- W4293731510 hasConceptScore W4293731510C74193536 @default.
- W4293731510 hasConceptScore W4293731510C87360688 @default.
- W4293731510 hasConceptScore W4293731510C89600930 @default.
- W4293731510 hasConceptScore W4293731510C97931131 @default.
- W4293731510 hasFunder F4320321001 @default.
- W4293731510 hasLocation W42937315101 @default.
- W4293731510 hasOpenAccess W4293731510 @default.
- W4293731510 hasPrimaryLocation W42937315101 @default.
- W4293731510 hasRelatedWork W1964120219 @default.
- W4293731510 hasRelatedWork W2005437358 @default.
- W4293731510 hasRelatedWork W2024160000 @default.
- W4293731510 hasRelatedWork W2061273563 @default.
- W4293731510 hasRelatedWork W2285052147 @default.
- W4293731510 hasRelatedWork W2517104666 @default.
- W4293731510 hasRelatedWork W2729514902 @default.
- W4293731510 hasRelatedWork W2773500201 @default.