Matches in SemOpenAlex for { <https://semopenalex.org/work/W2905312821> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2905312821 abstract "Recently, convolutional neural networks have shown powerful capability in different fields of computer vision, and have become the most effective means for dense prediction problems such as semantic segmentation. However, methods based on fully convolution network(FCN) are inherently limited to the size of the receptive field for each pixel, which leads to the bad performance of predicting object boundary. In this paper, we propose a novel deep neural network module, namely group dilated convolution(GDC), to effectively enlarge the receptive field, and a top-to-down pathway network is exploited simultaneously. The idea is that dilation convolution with different ratios can cover features of different scales, which shows a significant Mean IOU improvement in comparison with the baseline network." @default.
- W2905312821 created "2018-12-22" @default.
- W2905312821 creator A5004094063 @default.
- W2905312821 creator A5026662451 @default.
- W2905312821 creator A5069045156 @default.
- W2905312821 creator A5082598478 @default.
- W2905312821 date "2017-11-01" @default.
- W2905312821 modified "2023-09-23" @default.
- W2905312821 title "Enlarging Effective Receptive Field of Convolutional Neural Networks for Better Semantic Segmentation" @default.
- W2905312821 cites W1610060839 @default.
- W2905312821 cites W1686810756 @default.
- W2905312821 cites W1745334888 @default.
- W2905312821 cites W1817277359 @default.
- W2905312821 cites W1903029394 @default.
- W2905312821 cites W1948751323 @default.
- W2905312821 cites W2031489346 @default.
- W2905312821 cites W2144794286 @default.
- W2905312821 cites W2155893237 @default.
- W2905312821 cites W2163605009 @default.
- W2905312821 cites W2194775991 @default.
- W2905312821 cites W2407521645 @default.
- W2905312821 cites W2412782625 @default.
- W2905312821 cites W2556967412 @default.
- W2905312821 cites W2560023338 @default.
- W2905312821 cites W2563705555 @default.
- W2905312821 cites W2592939477 @default.
- W2905312821 cites W2599180264 @default.
- W2905312821 cites W2613718673 @default.
- W2905312821 cites W2962850830 @default.
- W2905312821 cites W2962992847 @default.
- W2905312821 cites W2963840672 @default.
- W2905312821 cites W2963881378 @default.
- W2905312821 cites W2964288706 @default.
- W2905312821 doi "https://doi.org/10.1109/acpr.2017.7" @default.
- W2905312821 hasPublicationYear "2017" @default.
- W2905312821 type Work @default.
- W2905312821 sameAs 2905312821 @default.
- W2905312821 citedByCount "4" @default.
- W2905312821 countsByYear W29053128212019 @default.
- W2905312821 countsByYear W29053128212021 @default.
- W2905312821 countsByYear W29053128212022 @default.
- W2905312821 crossrefType "proceedings-article" @default.
- W2905312821 hasAuthorship W2905312821A5004094063 @default.
- W2905312821 hasAuthorship W2905312821A5026662451 @default.
- W2905312821 hasAuthorship W2905312821A5069045156 @default.
- W2905312821 hasAuthorship W2905312821A5082598478 @default.
- W2905312821 hasConcept C124504099 @default.
- W2905312821 hasConcept C153180895 @default.
- W2905312821 hasConcept C154945302 @default.
- W2905312821 hasConcept C19071747 @default.
- W2905312821 hasConcept C202444582 @default.
- W2905312821 hasConcept C31972630 @default.
- W2905312821 hasConcept C33923547 @default.
- W2905312821 hasConcept C41008148 @default.
- W2905312821 hasConcept C81363708 @default.
- W2905312821 hasConcept C89600930 @default.
- W2905312821 hasConcept C9652623 @default.
- W2905312821 hasConceptScore W2905312821C124504099 @default.
- W2905312821 hasConceptScore W2905312821C153180895 @default.
- W2905312821 hasConceptScore W2905312821C154945302 @default.
- W2905312821 hasConceptScore W2905312821C19071747 @default.
- W2905312821 hasConceptScore W2905312821C202444582 @default.
- W2905312821 hasConceptScore W2905312821C31972630 @default.
- W2905312821 hasConceptScore W2905312821C33923547 @default.
- W2905312821 hasConceptScore W2905312821C41008148 @default.
- W2905312821 hasConceptScore W2905312821C81363708 @default.
- W2905312821 hasConceptScore W2905312821C89600930 @default.
- W2905312821 hasConceptScore W2905312821C9652623 @default.
- W2905312821 hasLocation W29053128211 @default.
- W2905312821 hasOpenAccess W2905312821 @default.
- W2905312821 hasPrimaryLocation W29053128211 @default.
- W2905312821 hasRelatedWork W1669643531 @default.
- W2905312821 hasRelatedWork W1721780360 @default.
- W2905312821 hasRelatedWork W2110230079 @default.
- W2905312821 hasRelatedWork W2117664411 @default.
- W2905312821 hasRelatedWork W2117933325 @default.
- W2905312821 hasRelatedWork W2122581818 @default.
- W2905312821 hasRelatedWork W2159066190 @default.
- W2905312821 hasRelatedWork W2739874619 @default.
- W2905312821 hasRelatedWork W2979932740 @default.
- W2905312821 hasRelatedWork W1967061043 @default.
- W2905312821 isParatext "false" @default.
- W2905312821 isRetracted "false" @default.
- W2905312821 magId "2905312821" @default.
- W2905312821 workType "article" @default.