Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226175029> ?p ?o ?g. }
- W4226175029 endingPage "2093" @default.
- W4226175029 startingPage "2081" @default.
- W4226175029 abstract "Existing deep models for facade parsing often fail in classifying pixels in heavily occluded regions of facade images due to the difficulty in feature representation of these pixels. In this paper, we solve facade parsing with occlusions by progressive feature learning. To this end, we locate the regions contaminated by occlusions via Bayesian uncertainty evaluation on categorizing each pixel in these regions. Then, guided by the uncertainty, we propose an occlusion-immune facade parsing architecture in which we progressively re-express the features of pixels in each contaminated region from easy to hard. Specifically, the outside pixels, which have reliable context from visible areas, are re-expressed at early stages; the inner pixels are processed at late stages when their surroundings have been decontaminated at the earlier stages. In addition, at each stage, instead of using regular square convolution kernels, we design a context enhancement module (CEM) with directional strip kernels, which can aggregate structural context to re-express facade pixels. Extensive experiments on popular facade datasets demonstrate that the proposed method achieves state-of-the-art performance." @default.
- W4226175029 created "2022-05-05" @default.
- W4226175029 creator A5007238584 @default.
- W4226175029 creator A5009533191 @default.
- W4226175029 creator A5011919230 @default.
- W4226175029 creator A5017031914 @default.
- W4226175029 creator A5032952854 @default.
- W4226175029 date "2022-01-01" @default.
- W4226175029 modified "2023-10-13" @default.
- W4226175029 title "Progressive Feature Learning for Facade Parsing With Occlusions" @default.
- W4226175029 cites W1587332854 @default.
- W4226175029 cites W1623823 @default.
- W4226175029 cites W1903029394 @default.
- W4226175029 cites W1935891383 @default.
- W4226175029 cites W1970015848 @default.
- W4226175029 cites W2048270193 @default.
- W4226175029 cites W2111051539 @default.
- W4226175029 cites W2115878665 @default.
- W4226175029 cites W2122132455 @default.
- W4226175029 cites W2148052781 @default.
- W4226175029 cites W2154069107 @default.
- W4226175029 cites W2194775991 @default.
- W4226175029 cites W2227923149 @default.
- W4226175029 cites W2285214964 @default.
- W4226175029 cites W2296073425 @default.
- W4226175029 cites W2560023338 @default.
- W4226175029 cites W2598666589 @default.
- W4226175029 cites W2741074234 @default.
- W4226175029 cites W2773966508 @default.
- W4226175029 cites W2805238701 @default.
- W4226175029 cites W2883989448 @default.
- W4226175029 cites W2896434438 @default.
- W4226175029 cites W2955058313 @default.
- W4226175029 cites W2963091558 @default.
- W4226175029 cites W2963881378 @default.
- W4226175029 cites W2964017310 @default.
- W4226175029 cites W2964148878 @default.
- W4226175029 cites W2990886896 @default.
- W4226175029 cites W2991377405 @default.
- W4226175029 cites W2997095758 @default.
- W4226175029 cites W3004811588 @default.
- W4226175029 cites W3027028760 @default.
- W4226175029 cites W3035512475 @default.
- W4226175029 cites W3048553410 @default.
- W4226175029 cites W3095638603 @default.
- W4226175029 cites W3101380508 @default.
- W4226175029 cites W3106480066 @default.
- W4226175029 cites W3108812909 @default.
- W4226175029 cites W3122507398 @default.
- W4226175029 cites W4245577215 @default.
- W4226175029 doi "https://doi.org/10.1109/tip.2022.3152004" @default.
- W4226175029 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35196233" @default.
- W4226175029 hasPublicationYear "2022" @default.
- W4226175029 type Work @default.
- W4226175029 citedByCount "6" @default.
- W4226175029 countsByYear W42261750292022 @default.
- W4226175029 countsByYear W42261750292023 @default.
- W4226175029 crossrefType "journal-article" @default.
- W4226175029 hasAuthorship W4226175029A5007238584 @default.
- W4226175029 hasAuthorship W4226175029A5009533191 @default.
- W4226175029 hasAuthorship W4226175029A5011919230 @default.
- W4226175029 hasAuthorship W4226175029A5017031914 @default.
- W4226175029 hasAuthorship W4226175029A5032952854 @default.
- W4226175029 hasConcept C127413603 @default.
- W4226175029 hasConcept C138885662 @default.
- W4226175029 hasConcept C153180895 @default.
- W4226175029 hasConcept C154945302 @default.
- W4226175029 hasConcept C160633673 @default.
- W4226175029 hasConcept C166957645 @default.
- W4226175029 hasConcept C186644900 @default.
- W4226175029 hasConcept C205649164 @default.
- W4226175029 hasConcept C2776401178 @default.
- W4226175029 hasConcept C2779343474 @default.
- W4226175029 hasConcept C2780113678 @default.
- W4226175029 hasConcept C31972630 @default.
- W4226175029 hasConcept C41008148 @default.
- W4226175029 hasConcept C41895202 @default.
- W4226175029 hasConcept C52622490 @default.
- W4226175029 hasConcept C66938386 @default.
- W4226175029 hasConceptScore W4226175029C127413603 @default.
- W4226175029 hasConceptScore W4226175029C138885662 @default.
- W4226175029 hasConceptScore W4226175029C153180895 @default.
- W4226175029 hasConceptScore W4226175029C154945302 @default.
- W4226175029 hasConceptScore W4226175029C160633673 @default.
- W4226175029 hasConceptScore W4226175029C166957645 @default.
- W4226175029 hasConceptScore W4226175029C186644900 @default.
- W4226175029 hasConceptScore W4226175029C205649164 @default.
- W4226175029 hasConceptScore W4226175029C2776401178 @default.
- W4226175029 hasConceptScore W4226175029C2779343474 @default.
- W4226175029 hasConceptScore W4226175029C2780113678 @default.
- W4226175029 hasConceptScore W4226175029C31972630 @default.
- W4226175029 hasConceptScore W4226175029C41008148 @default.
- W4226175029 hasConceptScore W4226175029C41895202 @default.
- W4226175029 hasConceptScore W4226175029C52622490 @default.
- W4226175029 hasConceptScore W4226175029C66938386 @default.
- W4226175029 hasFunder F4320321001 @default.
- W4226175029 hasLocation W42261750291 @default.
- W4226175029 hasLocation W42261750292 @default.