Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225535276> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4225535276 endingPage "2709" @default.
- W4225535276 startingPage "2695" @default.
- W4225535276 abstract "The existing publicly available datasets with pixel-level labels contain limited categories, and it is difficult to generalize to the real world containing thousands of categories. In this paper, we propose an approach to generate object masks with detailed pixel-level structures/boundaries automatically to enable semantic image segmentation of thousands of targets in the real world without manually labelling. A Guided Filter Network (GFN) is first developed to learn the segmentation knowledge from an existed dataset, and such GFN then transfers the learned segmentation knowledge to generate initial coarse object masks for the target images. These coarse object masks are treated as pseudo labels to self-optimize the GFN iteratively in the target images. Our experiments on six image sets have demonstrated that our proposed approach can generate object masks with detailed pixel-level structures/boundaries, whose quality is comparable to the manually-labelled ones. Our proposed approach also achieves better performance on semantic image segmentation than most existing weakly-supervised, semi-supervised, and domain adaptation approaches under the same experimental conditions." @default.
- W4225535276 created "2022-05-05" @default.
- W4225535276 creator A5008166952 @default.
- W4225535276 creator A5017775910 @default.
- W4225535276 creator A5031804038 @default.
- W4225535276 creator A5066572238 @default.
- W4225535276 creator A5076699095 @default.
- W4225535276 date "2022-01-01" @default.
- W4225535276 modified "2023-09-24" @default.
- W4225535276 title "Guided Filter Network for Semantic Image Segmentation" @default.
- W4225535276 doi "https://doi.org/10.1109/tip.2022.3160399" @default.
- W4225535276 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35320103" @default.
- W4225535276 hasPublicationYear "2022" @default.
- W4225535276 type Work @default.
- W4225535276 citedByCount "3" @default.
- W4225535276 countsByYear W42255352762022 @default.
- W4225535276 countsByYear W42255352762023 @default.
- W4225535276 crossrefType "journal-article" @default.
- W4225535276 hasAuthorship W4225535276A5008166952 @default.
- W4225535276 hasAuthorship W4225535276A5017775910 @default.
- W4225535276 hasAuthorship W4225535276A5031804038 @default.
- W4225535276 hasAuthorship W4225535276A5066572238 @default.
- W4225535276 hasAuthorship W4225535276A5076699095 @default.
- W4225535276 hasConcept C106131492 @default.
- W4225535276 hasConcept C115961682 @default.
- W4225535276 hasConcept C124504099 @default.
- W4225535276 hasConcept C153180895 @default.
- W4225535276 hasConcept C154945302 @default.
- W4225535276 hasConcept C160633673 @default.
- W4225535276 hasConcept C25694479 @default.
- W4225535276 hasConcept C2781238097 @default.
- W4225535276 hasConcept C31972630 @default.
- W4225535276 hasConcept C41008148 @default.
- W4225535276 hasConcept C65885262 @default.
- W4225535276 hasConcept C89600930 @default.
- W4225535276 hasConceptScore W4225535276C106131492 @default.
- W4225535276 hasConceptScore W4225535276C115961682 @default.
- W4225535276 hasConceptScore W4225535276C124504099 @default.
- W4225535276 hasConceptScore W4225535276C153180895 @default.
- W4225535276 hasConceptScore W4225535276C154945302 @default.
- W4225535276 hasConceptScore W4225535276C160633673 @default.
- W4225535276 hasConceptScore W4225535276C25694479 @default.
- W4225535276 hasConceptScore W4225535276C2781238097 @default.
- W4225535276 hasConceptScore W4225535276C31972630 @default.
- W4225535276 hasConceptScore W4225535276C41008148 @default.
- W4225535276 hasConceptScore W4225535276C65885262 @default.
- W4225535276 hasConceptScore W4225535276C89600930 @default.
- W4225535276 hasFunder F4320321001 @default.
- W4225535276 hasFunder F4320321543 @default.
- W4225535276 hasFunder F4320324173 @default.
- W4225535276 hasLocation W42255352761 @default.
- W4225535276 hasLocation W42255352762 @default.
- W4225535276 hasOpenAccess W4225535276 @default.
- W4225535276 hasPrimaryLocation W42255352761 @default.
- W4225535276 hasRelatedWork W1507266234 @default.
- W4225535276 hasRelatedWork W1631910785 @default.
- W4225535276 hasRelatedWork W1669643531 @default.
- W4225535276 hasRelatedWork W1963494852 @default.
- W4225535276 hasRelatedWork W2026019026 @default.
- W4225535276 hasRelatedWork W2069711651 @default.
- W4225535276 hasRelatedWork W2549936415 @default.
- W4225535276 hasRelatedWork W2558375057 @default.
- W4225535276 hasRelatedWork W2739874619 @default.
- W4225535276 hasRelatedWork W1967061043 @default.
- W4225535276 hasVolume "31" @default.
- W4225535276 isParatext "false" @default.
- W4225535276 isRetracted "false" @default.
- W4225535276 workType "article" @default.