Matches in SemOpenAlex for { <https://semopenalex.org/work/W3018135903> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3018135903 abstract "We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. Building on the recently proposed Self-Constructing Graph (SCG) module, which makes use of learnable latent variables to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs, we leverage multiple views in order to explicitly exploit the rotational invariance in airborne images. We further develop an adaptive class weighting loss to address the class imbalance. We demonstrate the effectiveness and flexibility of the proposed method on the Agriculture-Vision challenge dataset and our model achieves very competitive results (0.547 mIoU) with much fewer parameters and at a lower computational cost compared to related pure-CNN based work. Code will be available at: github.com/samleoqh/MSCG-Net" @default.
- W3018135903 created "2020-05-01" @default.
- W3018135903 creator A5013414039 @default.
- W3018135903 creator A5023225712 @default.
- W3018135903 creator A5051497938 @default.
- W3018135903 creator A5084672445 @default.
- W3018135903 date "2020-04-21" @default.
- W3018135903 modified "2023-10-16" @default.
- W3018135903 title "Multi-view Self-Constructing Graph Convolutional Networks with Adaptive Class Weighting Loss for Semantic Segmentation" @default.
- W3018135903 cites W1903029394 @default.
- W3018135903 cites W2480078828 @default.
- W3018135903 cites W2519887557 @default.
- W3018135903 cites W2554952599 @default.
- W3018135903 cites W2558748708 @default.
- W3018135903 cites W2892220259 @default.
- W3018135903 cites W2951004968 @default.
- W3018135903 cites W2962837172 @default.
- W3018135903 cites W2962914239 @default.
- W3018135903 cites W2963420686 @default.
- W3018135903 cites W2964121744 @default.
- W3018135903 cites W2964153283 @default.
- W3018135903 cites W2970803838 @default.
- W3018135903 cites W2979300990 @default.
- W3018135903 cites W2979750740 @default.
- W3018135903 cites W3009297390 @default.
- W3018135903 cites W3011648503 @default.
- W3018135903 cites W3034534947 @default.
- W3018135903 doi "https://doi.org/10.48550/arxiv.2004.10327" @default.
- W3018135903 hasPublicationYear "2020" @default.
- W3018135903 type Work @default.
- W3018135903 sameAs 3018135903 @default.
- W3018135903 citedByCount "0" @default.
- W3018135903 crossrefType "posted-content" @default.
- W3018135903 hasAuthorship W3018135903A5013414039 @default.
- W3018135903 hasAuthorship W3018135903A5023225712 @default.
- W3018135903 hasAuthorship W3018135903A5051497938 @default.
- W3018135903 hasAuthorship W3018135903A5084672445 @default.
- W3018135903 hasBestOaLocation W30181359031 @default.
- W3018135903 hasConcept C119857082 @default.
- W3018135903 hasConcept C126838900 @default.
- W3018135903 hasConcept C132525143 @default.
- W3018135903 hasConcept C153083717 @default.
- W3018135903 hasConcept C153180895 @default.
- W3018135903 hasConcept C154945302 @default.
- W3018135903 hasConcept C165696696 @default.
- W3018135903 hasConcept C177264268 @default.
- W3018135903 hasConcept C183115368 @default.
- W3018135903 hasConcept C199360897 @default.
- W3018135903 hasConcept C2776760102 @default.
- W3018135903 hasConcept C2777212361 @default.
- W3018135903 hasConcept C2780801425 @default.
- W3018135903 hasConcept C38652104 @default.
- W3018135903 hasConcept C41008148 @default.
- W3018135903 hasConcept C71924100 @default.
- W3018135903 hasConcept C80444323 @default.
- W3018135903 hasConcept C89600930 @default.
- W3018135903 hasConceptScore W3018135903C119857082 @default.
- W3018135903 hasConceptScore W3018135903C126838900 @default.
- W3018135903 hasConceptScore W3018135903C132525143 @default.
- W3018135903 hasConceptScore W3018135903C153083717 @default.
- W3018135903 hasConceptScore W3018135903C153180895 @default.
- W3018135903 hasConceptScore W3018135903C154945302 @default.
- W3018135903 hasConceptScore W3018135903C165696696 @default.
- W3018135903 hasConceptScore W3018135903C177264268 @default.
- W3018135903 hasConceptScore W3018135903C183115368 @default.
- W3018135903 hasConceptScore W3018135903C199360897 @default.
- W3018135903 hasConceptScore W3018135903C2776760102 @default.
- W3018135903 hasConceptScore W3018135903C2777212361 @default.
- W3018135903 hasConceptScore W3018135903C2780801425 @default.
- W3018135903 hasConceptScore W3018135903C38652104 @default.
- W3018135903 hasConceptScore W3018135903C41008148 @default.
- W3018135903 hasConceptScore W3018135903C71924100 @default.
- W3018135903 hasConceptScore W3018135903C80444323 @default.
- W3018135903 hasConceptScore W3018135903C89600930 @default.
- W3018135903 hasLocation W30181359031 @default.
- W3018135903 hasLocation W30181359032 @default.
- W3018135903 hasOpenAccess W3018135903 @default.
- W3018135903 hasPrimaryLocation W30181359031 @default.
- W3018135903 hasRelatedWork W2063855213 @default.
- W3018135903 hasRelatedWork W2510758617 @default.
- W3018135903 hasRelatedWork W2603501458 @default.
- W3018135903 hasRelatedWork W2897195263 @default.
- W3018135903 hasRelatedWork W2936547201 @default.
- W3018135903 hasRelatedWork W2948262272 @default.
- W3018135903 hasRelatedWork W4206076898 @default.
- W3018135903 hasRelatedWork W4281569454 @default.
- W3018135903 hasRelatedWork W4300659434 @default.
- W3018135903 hasRelatedWork W4307291644 @default.
- W3018135903 isParatext "false" @default.
- W3018135903 isRetracted "false" @default.
- W3018135903 magId "3018135903" @default.
- W3018135903 workType "article" @default.