Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896435145> ?p ?o ?g. }
- W2896435145 abstract "Weakly-supervised semantic image segmentation suffers from lacking accurate pixel-level annotations. In this paper, we propose a novel graph convolutional network-based method, called GraphNet, to learn pixel-wise labels from weak annotations. Firstly, we construct a graph on the superpixels of a training image by combining the low-level spatial relation and high-level semantic content. Meanwhile, scribble or bounding box annotations are embedded into the graph, respectively. Then, GraphNet takes the graph as input and learns to predict high-confidence pseudo image masks by a convolutional network operating directly on graphs. At last, a segmentation network is trained supervised by these pseudo image masks. We comprehensively conduct experiments on the PASCAL VOC 2012 and PASCAL-CONTEXT segmentation benchmarks. Experimental results demonstrate that GraphNet is effective to predict the pixel labels with scribble or bounding box annotations. The proposed framework yields state-of-the-art results in the community." @default.
- W2896435145 created "2018-10-26" @default.
- W2896435145 creator A5005101751 @default.
- W2896435145 creator A5019596093 @default.
- W2896435145 creator A5043641380 @default.
- W2896435145 creator A5047821546 @default.
- W2896435145 date "2018-10-15" @default.
- W2896435145 modified "2023-10-09" @default.
- W2896435145 title "GraphNet" @default.
- W2896435145 cites W1495267108 @default.
- W2896435145 cites W1783315696 @default.
- W2896435145 cites W1903029394 @default.
- W2896435145 cites W1945608308 @default.
- W2896435145 cites W1983546589 @default.
- W2896435145 cites W1991367009 @default.
- W2896435145 cites W1999478155 @default.
- W2896435145 cites W2013101727 @default.
- W2896435145 cites W2024733009 @default.
- W2896435145 cites W2037227137 @default.
- W2896435145 cites W2075695045 @default.
- W2896435145 cites W2108598243 @default.
- W2896435145 cites W2118246710 @default.
- W2896435145 cites W2119300483 @default.
- W2896435145 cites W2125215748 @default.
- W2896435145 cites W2144794286 @default.
- W2896435145 cites W2158787690 @default.
- W2896435145 cites W2203062554 @default.
- W2896435145 cites W2221898772 @default.
- W2896435145 cites W2291422229 @default.
- W2896435145 cites W2295107390 @default.
- W2896435145 cites W2309415944 @default.
- W2896435145 cites W2337429362 @default.
- W2896435145 cites W2468480815 @default.
- W2896435145 cites W2560023338 @default.
- W2896435145 cites W2585747585 @default.
- W2896435145 cites W2605214291 @default.
- W2896435145 cites W2963165299 @default.
- W2896435145 cites W2963198662 @default.
- W2896435145 cites W2963758239 @default.
- W2896435145 cites W2964309882 @default.
- W2896435145 cites W3100040694 @default.
- W2896435145 doi "https://doi.org/10.1145/3240508.3240542" @default.
- W2896435145 hasPublicationYear "2018" @default.
- W2896435145 type Work @default.
- W2896435145 sameAs 2896435145 @default.
- W2896435145 citedByCount "25" @default.
- W2896435145 countsByYear W28964351452019 @default.
- W2896435145 countsByYear W28964351452020 @default.
- W2896435145 countsByYear W28964351452021 @default.
- W2896435145 countsByYear W28964351452022 @default.
- W2896435145 countsByYear W28964351452023 @default.
- W2896435145 crossrefType "proceedings-article" @default.
- W2896435145 hasAuthorship W2896435145A5005101751 @default.
- W2896435145 hasAuthorship W2896435145A5019596093 @default.
- W2896435145 hasAuthorship W2896435145A5043641380 @default.
- W2896435145 hasAuthorship W2896435145A5047821546 @default.
- W2896435145 hasConcept C115961682 @default.
- W2896435145 hasConcept C124504099 @default.
- W2896435145 hasConcept C132525143 @default.
- W2896435145 hasConcept C147037132 @default.
- W2896435145 hasConcept C153180895 @default.
- W2896435145 hasConcept C154945302 @default.
- W2896435145 hasConcept C160633673 @default.
- W2896435145 hasConcept C179372163 @default.
- W2896435145 hasConcept C199360897 @default.
- W2896435145 hasConcept C205711294 @default.
- W2896435145 hasConcept C41008148 @default.
- W2896435145 hasConcept C63584917 @default.
- W2896435145 hasConcept C75608658 @default.
- W2896435145 hasConcept C80444323 @default.
- W2896435145 hasConcept C81363708 @default.
- W2896435145 hasConcept C89600930 @default.
- W2896435145 hasConceptScore W2896435145C115961682 @default.
- W2896435145 hasConceptScore W2896435145C124504099 @default.
- W2896435145 hasConceptScore W2896435145C132525143 @default.
- W2896435145 hasConceptScore W2896435145C147037132 @default.
- W2896435145 hasConceptScore W2896435145C153180895 @default.
- W2896435145 hasConceptScore W2896435145C154945302 @default.
- W2896435145 hasConceptScore W2896435145C160633673 @default.
- W2896435145 hasConceptScore W2896435145C179372163 @default.
- W2896435145 hasConceptScore W2896435145C199360897 @default.
- W2896435145 hasConceptScore W2896435145C205711294 @default.
- W2896435145 hasConceptScore W2896435145C41008148 @default.
- W2896435145 hasConceptScore W2896435145C63584917 @default.
- W2896435145 hasConceptScore W2896435145C75608658 @default.
- W2896435145 hasConceptScore W2896435145C80444323 @default.
- W2896435145 hasConceptScore W2896435145C81363708 @default.
- W2896435145 hasConceptScore W2896435145C89600930 @default.
- W2896435145 hasLocation W28964351451 @default.
- W2896435145 hasOpenAccess W2896435145 @default.
- W2896435145 hasPrimaryLocation W28964351451 @default.
- W2896435145 hasRelatedWork W1495267108 @default.
- W2896435145 hasRelatedWork W1994488211 @default.
- W2896435145 hasRelatedWork W2127194945 @default.
- W2896435145 hasRelatedWork W2756241593 @default.
- W2896435145 hasRelatedWork W2949086864 @default.
- W2896435145 hasRelatedWork W3034239110 @default.
- W2896435145 hasRelatedWork W3143270224 @default.
- W2896435145 hasRelatedWork W3156520185 @default.
- W2896435145 hasRelatedWork W3161467835 @default.