FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971503239> ?p ?o ?g. }

• W2971503239 endingPage "2122" @default.
• W2971503239 startingPage "2108" @default.
• W2971503239 abstract "Convolutional operator learning is gaining attention in many signal processing and computer vision applications. Learning kernels has mostly relied on so-called patch-domain approaches that extract and store many overlapping patches across training signals. Due to memory demands, patch-domain methods have limitations when learning kernels from large datasets -- particularly with multi-layered structures, e.g., convolutional neural networks -- or when applying the learned kernels to high-dimensional signal recovery problems. The so-called convolution approach does not store many overlapping patches, and thus overcomes the memory problems particularly with careful algorithmic designs; it has been studied within the synthesis signal model, e.g., convolutional dictionary learning. This paper proposes a new convolutional analysis operator learning (CAOL) framework that learns an analysis sparsifying regularizer with the convolution perspective, and develops a new convergent Block Proximal Extrapolated Gradient method using a Majorizer (BPEG-M) to solve the corresponding block multi-nonconvex problems. To learn diverse filters within the CAOL framework, this paper introduces an orthogonality constraint that enforces a tight-frame filter condition, and a regularizer that promotes diversity between filters. Numerical experiments show that, with sharp majorizers, BPEG-M significantly accelerates the CAOL convergence rate compared to the state-of-the-art block proximal gradient (BPG) method. Numerical experiments for sparse-view computational tomography show that a convolutional sparsifying regularizer learned via CAOL significantly improves reconstruction quality compared to a conventional edge-preserving regularizer. Using more and wider kernels in a learned regularizer better preserves edges in reconstructed images." @default.
• W2971503239 created "2019-09-12" @default.
• W2971503239 creator A5020501362 @default.
• W2971503239 creator A5027207271 @default.
• W2971503239 date "2020-01-01" @default.
• W2971503239 modified "2023-10-03" @default.
• W2971503239 title "Convolutional Analysis Operator Learning: Acceleration and Convergence" @default.
• W2971503239 cites W1540764732 @default.
• W2971503239 cites W180242331 @default.
• W2971503239 cites W1906770428 @default.
• W2971503239 cites W1915372217 @default.
• W2971503239 cites W1946953458 @default.
• W2971503239 cites W1968154520 @default.
• W2971503239 cites W1999829977 @default.
• W2971503239 cites W2005876975 @default.
• W2971503239 cites W2045096911 @default.
• W2971503239 cites W2053958583 @default.
• W2971503239 cites W2087332491 @default.
• W2971503239 cites W2090457307 @default.
• W2971503239 cites W2094366314 @default.
• W2971503239 cites W2100556411 @default.
• W2971503239 cites W2112796928 @default.
• W2971503239 cites W2114083954 @default.
• W2971503239 cites W2117259536 @default.
• W2971503239 cites W2120047933 @default.
• W2971503239 cites W2121570028 @default.
• W2971503239 cites W2123870301 @default.
• W2971503239 cites W2125527601 @default.
• W2971503239 cites W2127114523 @default.
• W2971503239 cites W2127447444 @default.
• W2971503239 cites W2130129583 @default.
• W2971503239 cites W2133665775 @default.
• W2971503239 cites W2136485351 @default.
• W2971503239 cites W2140742952 @default.
• W2971503239 cites W2145889472 @default.
• W2971503239 cites W2146842127 @default.
• W2971503239 cites W2153663612 @default.
• W2971503239 cites W2160547390 @default.
• W2971503239 cites W2161305109 @default.
• W2971503239 cites W2171004446 @default.
• W2971503239 cites W2190662802 @default.
• W2971503239 cites W2293078015 @default.
• W2971503239 cites W2546302380 @default.
• W2971503239 cites W2573726823 @default.
• W2971503239 cites W2613155248 @default.
• W2971503239 cites W2710262087 @default.
• W2971503239 cites W2732096896 @default.
• W2971503239 cites W2733076523 @default.
• W2971503239 cites W2752939138 @default.
• W2971503239 cites W2754956769 @default.
• W2971503239 cites W2793419304 @default.
• W2971503239 cites W2888917483 @default.
• W2971503239 cites W2913806414 @default.
• W2971503239 cites W2952020389 @default.
• W2971503239 cites W2963648037 @default.
• W2971503239 cites W2963739187 @default.
• W2971503239 cites W2963769724 @default.
• W2971503239 cites W2964188306 @default.
• W2971503239 cites W2964215687 @default.
• W2971503239 cites W3100455090 @default.
• W2971503239 cites W3101684528 @default.
• W2971503239 cites W4206310440 @default.
• W2971503239 cites W4255521522 @default.
• W2971503239 doi "https://doi.org/10.1109/tip.2019.2937734" @default.
• W2971503239 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7170176" @default.
• W2971503239 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31484120" @default.
• W2971503239 hasPublicationYear "2020" @default.
• W2971503239 type Work @default.
• W2971503239 sameAs 2971503239 @default.
• W2971503239 citedByCount "38" @default.
• W2971503239 countsByYear W29715032392017 @default.
• W2971503239 countsByYear W29715032392018 @default.
• W2971503239 countsByYear W29715032392019 @default.
• W2971503239 countsByYear W29715032392020 @default.
• W2971503239 countsByYear W29715032392021 @default.
• W2971503239 countsByYear W29715032392022 @default.
• W2971503239 countsByYear W29715032392023 @default.
• W2971503239 crossrefType "journal-article" @default.
• W2971503239 hasAuthorship W2971503239A5020501362 @default.
• W2971503239 hasAuthorship W2971503239A5027207271 @default.
• W2971503239 hasBestOaLocation W29715032391 @default.
• W2971503239 hasConcept C104317684 @default.
• W2971503239 hasConcept C11413529 @default.
• W2971503239 hasConcept C114614502 @default.
• W2971503239 hasConcept C153180895 @default.
• W2971503239 hasConcept C154945302 @default.
• W2971503239 hasConcept C157899210 @default.
• W2971503239 hasConcept C158448853 @default.
• W2971503239 hasConcept C162324750 @default.
• W2971503239 hasConcept C17020691 @default.
• W2971503239 hasConcept C17137986 @default.
• W2971503239 hasConcept C185592680 @default.
• W2971503239 hasConcept C2524010 @default.
• W2971503239 hasConcept C2777210771 @default.
• W2971503239 hasConcept C2777303404 @default.
• W2971503239 hasConcept C33923547 @default.
• W2971503239 hasConcept C41008148 @default.
• W2971503239 hasConcept C45347329 @default.

• next