Matches in SemOpenAlex for { <https://semopenalex.org/work/W2906033943> ?p ?o ?g. }
- W2906033943 abstract "Deep networks are nowadays becoming popular in many computer vision and pattern recognition tasks. Among these networks, deep kernels are particularly interesting and effective, however, their computational complexity is a major issue especially on cheap hardware resources. 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.
- W2906033943 created "2019-01-01" @default.
- W2906033943 creator A5029896607 @default.
- W2906033943 date "2018-12-21" @default.
- W2906033943 modified "2023-09-27" @default.
- W2906033943 title "Cascaded Coarse-to-Fine Deep Kernel Networks for Efficient Satellite Image Change Detection." @default.
- W2906033943 cites W130653142 @default.
- W2906033943 cites W1563088657 @default.
- W2906033943 cites W1601437336 @default.
- W2906033943 cites W1605688901 @default.
- W2906033943 cites W1677182931 @default.
- W2906033943 cites W167790647 @default.
- W2906033943 cites W1686810756 @default.
- W2906033943 cites W1746680969 @default.
- W2906033943 cites W1777628566 @default.
- W2906033943 cites W1910567995 @default.
- W2906033943 cites W1934410531 @default.
- W2906033943 cites W1967170228 @default.
- W2906033943 cites W1983988843 @default.
- W2906033943 cites W2003497265 @default.
- W2906033943 cites W2031823405 @default.
- W2906033943 cites W2039182213 @default.
- W2906033943 cites W2046991152 @default.
- W2906033943 cites W2048818249 @default.
- W2906033943 cites W2050113278 @default.
- W2906033943 cites W2089902864 @default.
- W2906033943 cites W2095618661 @default.
- W2906033943 cites W2097117768 @default.
- W2906033943 cites W2102605133 @default.
- W2906033943 cites W2111073379 @default.
- W2906033943 cites W2112562896 @default.
- W2906033943 cites W2117539524 @default.
- W2906033943 cites W2127711253 @default.
- W2906033943 cites W2137055149 @default.
- W2906033943 cites W2140274257 @default.
- W2906033943 cites W2143338212 @default.
- W2906033943 cites W2145287260 @default.
- W2906033943 cites W2150341604 @default.
- W2906033943 cites W2167215970 @default.
- W2906033943 cites W2169625877 @default.
- W2906033943 cites W2194775991 @default.
- W2906033943 cites W2222792052 @default.
- W2906033943 cites W2285660444 @default.
- W2906033943 cites W2308045930 @default.
- W2906033943 cites W2399164823 @default.
- W2906033943 cites W2513419314 @default.
- W2906033943 cites W2587063199 @default.
- W2906033943 cites W2593303827 @default.
- W2906033943 cites W2607538525 @default.
- W2906033943 cites W2735189290 @default.
- W2906033943 cites W2949578333 @default.
- W2906033943 cites W2951784944 @default.
- W2906033943 cites W2963674932 @default.
- W2906033943 cites W2964135722 @default.
- W2906033943 cites W2964299589 @default.
- W2906033943 cites W3193477162 @default.
- W2906033943 hasPublicationYear "2018" @default.
- W2906033943 type Work @default.
- W2906033943 sameAs 2906033943 @default.
- W2906033943 citedByCount "0" @default.
- W2906033943 crossrefType "posted-content" @default.
- W2906033943 hasAuthorship W2906033943A5029896607 @default.
- W2906033943 hasConcept C106301342 @default.
- W2906033943 hasConcept C108583219 @default.
- W2906033943 hasConcept C113775141 @default.
- W2906033943 hasConcept C11413529 @default.
- W2906033943 hasConcept C114614502 @default.
- W2906033943 hasConcept C121332964 @default.
- W2906033943 hasConcept C153180895 @default.
- W2906033943 hasConcept C154945302 @default.
- W2906033943 hasConcept C179799912 @default.
- W2906033943 hasConcept C185592680 @default.
- W2906033943 hasConcept C2984842247 @default.
- W2906033943 hasConcept C33923547 @default.
- W2906033943 hasConcept C34146451 @default.
- W2906033943 hasConcept C41008148 @default.
- W2906033943 hasConcept C43617362 @default.
- W2906033943 hasConcept C45374587 @default.
- W2906033943 hasConcept C62520636 @default.
- W2906033943 hasConcept C74193536 @default.
- W2906033943 hasConceptScore W2906033943C106301342 @default.
- W2906033943 hasConceptScore W2906033943C108583219 @default.
- W2906033943 hasConceptScore W2906033943C113775141 @default.
- W2906033943 hasConceptScore W2906033943C11413529 @default.
- W2906033943 hasConceptScore W2906033943C114614502 @default.
- W2906033943 hasConceptScore W2906033943C121332964 @default.
- W2906033943 hasConceptScore W2906033943C153180895 @default.
- W2906033943 hasConceptScore W2906033943C154945302 @default.
- W2906033943 hasConceptScore W2906033943C179799912 @default.
- W2906033943 hasConceptScore W2906033943C185592680 @default.
- W2906033943 hasConceptScore W2906033943C2984842247 @default.
- W2906033943 hasConceptScore W2906033943C33923547 @default.
- W2906033943 hasConceptScore W2906033943C34146451 @default.
- W2906033943 hasConceptScore W2906033943C41008148 @default.
- W2906033943 hasConceptScore W2906033943C43617362 @default.
- W2906033943 hasConceptScore W2906033943C45374587 @default.
- W2906033943 hasConceptScore W2906033943C62520636 @default.
- W2906033943 hasConceptScore W2906033943C74193536 @default.
- W2906033943 hasLocation W29060339431 @default.
- W2906033943 hasOpenAccess W2906033943 @default.