Matches in SemOpenAlex for { <https://semopenalex.org/work/W2769171608> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2769171608 abstract "In this paper, we address the issue of efficient computation in deep kernel networks. We propose a novel framework that reduces dramatically the complexity of evaluating these deep kernels. Our method is based on a coarse-to-fine cascade of networks designed for efficient computation; early stages of the cascade are cheap and reject many patterns efficiently while deep stages are more expensive and accurate. The design principle of these reduced complexity networks is based on a variant of the cross-entropy criterion that reduces the complexity of the networks in the cascade while preserving all the positive responses of the original kernel network. Experiments conducted - on the challenging and time demanding change detection task, on very large satellite images - show that our proposed coarse-to-fine approach is effective and highly efficient." @default.
- W2769171608 created "2017-12-04" @default.
- W2769171608 creator A5029896607 @default.
- W2769171608 date "2017-10-01" @default.
- W2769171608 modified "2023-09-30" @default.
- W2769171608 title "Coarse-to-Fine Deep Kernel Networks" @default.
- W2769171608 cites W1563088657 @default.
- W2769171608 cites W1601437336 @default.
- W2769171608 cites W1601741105 @default.
- W2769171608 cites W1677182931 @default.
- W2769171608 cites W1923404803 @default.
- W2769171608 cites W1967170228 @default.
- W2769171608 cites W1983364832 @default.
- W2769171608 cites W2016053056 @default.
- W2769171608 cites W2031823405 @default.
- W2769171608 cites W2074398519 @default.
- W2769171608 cites W2097117768 @default.
- W2769171608 cites W2117539524 @default.
- W2769171608 cites W2124722975 @default.
- W2769171608 cites W2139212933 @default.
- W2769171608 cites W2140274257 @default.
- W2769171608 cites W2143113048 @default.
- W2769171608 cites W2145908571 @default.
- W2769171608 cites W2194775991 @default.
- W2769171608 cites W2285660444 @default.
- W2769171608 cites W2395459784 @default.
- W2769171608 cites W2503931548 @default.
- W2769171608 cites W2587063199 @default.
- W2769171608 cites W2608434950 @default.
- W2769171608 cites W2735189290 @default.
- W2769171608 cites W3097096317 @default.
- W2769171608 cites W4205947740 @default.
- W2769171608 doi "https://doi.org/10.1109/iccvw.2017.137" @default.
- W2769171608 hasPublicationYear "2017" @default.
- W2769171608 type Work @default.
- W2769171608 sameAs 2769171608 @default.
- W2769171608 citedByCount "16" @default.
- W2769171608 countsByYear W27691716082018 @default.
- W2769171608 countsByYear W27691716082019 @default.
- W2769171608 countsByYear W27691716082020 @default.
- W2769171608 countsByYear W27691716082021 @default.
- W2769171608 countsByYear W27691716082022 @default.
- W2769171608 countsByYear W27691716082023 @default.
- W2769171608 crossrefType "proceedings-article" @default.
- W2769171608 hasAuthorship W2769171608A5029896607 @default.
- W2769171608 hasConcept C106301342 @default.
- W2769171608 hasConcept C108583219 @default.
- W2769171608 hasConcept C11413529 @default.
- W2769171608 hasConcept C114614502 @default.
- W2769171608 hasConcept C121332964 @default.
- W2769171608 hasConcept C127413603 @default.
- W2769171608 hasConcept C154945302 @default.
- W2769171608 hasConcept C179799912 @default.
- W2769171608 hasConcept C33923547 @default.
- W2769171608 hasConcept C34146451 @default.
- W2769171608 hasConcept C41008148 @default.
- W2769171608 hasConcept C42360764 @default.
- W2769171608 hasConcept C45374587 @default.
- W2769171608 hasConcept C62520636 @default.
- W2769171608 hasConcept C74193536 @default.
- W2769171608 hasConceptScore W2769171608C106301342 @default.
- W2769171608 hasConceptScore W2769171608C108583219 @default.
- W2769171608 hasConceptScore W2769171608C11413529 @default.
- W2769171608 hasConceptScore W2769171608C114614502 @default.
- W2769171608 hasConceptScore W2769171608C121332964 @default.
- W2769171608 hasConceptScore W2769171608C127413603 @default.
- W2769171608 hasConceptScore W2769171608C154945302 @default.
- W2769171608 hasConceptScore W2769171608C179799912 @default.
- W2769171608 hasConceptScore W2769171608C33923547 @default.
- W2769171608 hasConceptScore W2769171608C34146451 @default.
- W2769171608 hasConceptScore W2769171608C41008148 @default.
- W2769171608 hasConceptScore W2769171608C42360764 @default.
- W2769171608 hasConceptScore W2769171608C45374587 @default.
- W2769171608 hasConceptScore W2769171608C62520636 @default.
- W2769171608 hasConceptScore W2769171608C74193536 @default.
- W2769171608 hasLocation W27691716081 @default.
- W2769171608 hasOpenAccess W2769171608 @default.
- W2769171608 hasPrimaryLocation W27691716081 @default.
- W2769171608 hasRelatedWork W2126887587 @default.
- W2769171608 hasRelatedWork W2731899572 @default.
- W2769171608 hasRelatedWork W2939353110 @default.
- W2769171608 hasRelatedWork W3009238340 @default.
- W2769171608 hasRelatedWork W3215138031 @default.
- W2769171608 hasRelatedWork W4230611425 @default.
- W2769171608 hasRelatedWork W4312962853 @default.
- W2769171608 hasRelatedWork W4321369474 @default.
- W2769171608 hasRelatedWork W4327774331 @default.
- W2769171608 hasRelatedWork W4360585206 @default.
- W2769171608 isParatext "false" @default.
- W2769171608 isRetracted "false" @default.
- W2769171608 magId "2769171608" @default.
- W2769171608 workType "article" @default.