Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167277575> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3167277575 abstract "Semantic segmentation is a fundamental vision problem which aims to divide an image into non-overlapped regions and then assign them with predefined object labels. Despite its latest development (especially deep neural network-based), semantic segmentation is still far from comprehensive understanding of the visual world around us. For example, the obtained object labels are not fine-grained enough for solving more complicated vision tasks such as fine-grained retrieval with multiple attribute-based queries (e.g. the query ‘a bird’ along with the attribute ‘has wing colour: grey’). In this paper, we thus choose to study a more challenging vision problem called attribute segmentation, which aims to localize attributes within the targeted object (e.g. bird) in a given image. Due to the high cost of collecting pixel-level attribute annotations, we focus on weakly-supervised attribute segmentation (WSAS) that utilizes only image-level attribute labels for model training. Note that this new WSAS problem degrades to the conventional weakly-supervised semantic segmentation (WSSS) problem when attribute labels are considered as object labels. To overcome the attribute label noise caused by image-level weak supervision, we propose a novel sparse learning method for solving the WSAS problem. Extensive experiments demonstrate that the proposed WSAS method significantly outperforms the state-of-the-art WSSS and attribute localization methods." @default.
- W3167277575 created "2021-06-22" @default.
- W3167277575 creator A5007465667 @default.
- W3167277575 creator A5085349794 @default.
- W3167277575 date "2021-07-05" @default.
- W3167277575 modified "2023-09-23" @default.
- W3167277575 title "Weakly-Supervised Attribute Segmentation" @default.
- W3167277575 cites W1745334888 @default.
- W3167277575 cites W1903029394 @default.
- W3167277575 cites W1994488211 @default.
- W3167277575 cites W2051549110 @default.
- W3167277575 cites W2104657103 @default.
- W3167277575 cites W2118246710 @default.
- W3167277575 cites W2119605622 @default.
- W3167277575 cites W2211996548 @default.
- W3167277575 cites W2306289963 @default.
- W3167277575 cites W2554320282 @default.
- W3167277575 cites W2554816096 @default.
- W3167277575 cites W2557406251 @default.
- W3167277575 cites W2563705555 @default.
- W3167277575 cites W2738853914 @default.
- W3167277575 cites W2763070548 @default.
- W3167277575 cites W2799124825 @default.
- W3167277575 cites W2898491875 @default.
- W3167277575 cites W2963857746 @default.
- W3167277575 cites W2963977581 @default.
- W3167277575 cites W2986999591 @default.
- W3167277575 doi "https://doi.org/10.1109/icme51207.2021.9428190" @default.
- W3167277575 hasPublicationYear "2021" @default.
- W3167277575 type Work @default.
- W3167277575 sameAs 3167277575 @default.
- W3167277575 citedByCount "0" @default.
- W3167277575 crossrefType "proceedings-article" @default.
- W3167277575 hasAuthorship W3167277575A5007465667 @default.
- W3167277575 hasAuthorship W3167277575A5085349794 @default.
- W3167277575 hasConcept C108583219 @default.
- W3167277575 hasConcept C119857082 @default.
- W3167277575 hasConcept C120665830 @default.
- W3167277575 hasConcept C121332964 @default.
- W3167277575 hasConcept C124504099 @default.
- W3167277575 hasConcept C153180895 @default.
- W3167277575 hasConcept C154945302 @default.
- W3167277575 hasConcept C184337299 @default.
- W3167277575 hasConcept C192209626 @default.
- W3167277575 hasConcept C199360897 @default.
- W3167277575 hasConcept C2781238097 @default.
- W3167277575 hasConcept C31972630 @default.
- W3167277575 hasConcept C41008148 @default.
- W3167277575 hasConcept C50644808 @default.
- W3167277575 hasConcept C89600930 @default.
- W3167277575 hasConceptScore W3167277575C108583219 @default.
- W3167277575 hasConceptScore W3167277575C119857082 @default.
- W3167277575 hasConceptScore W3167277575C120665830 @default.
- W3167277575 hasConceptScore W3167277575C121332964 @default.
- W3167277575 hasConceptScore W3167277575C124504099 @default.
- W3167277575 hasConceptScore W3167277575C153180895 @default.
- W3167277575 hasConceptScore W3167277575C154945302 @default.
- W3167277575 hasConceptScore W3167277575C184337299 @default.
- W3167277575 hasConceptScore W3167277575C192209626 @default.
- W3167277575 hasConceptScore W3167277575C199360897 @default.
- W3167277575 hasConceptScore W3167277575C2781238097 @default.
- W3167277575 hasConceptScore W3167277575C31972630 @default.
- W3167277575 hasConceptScore W3167277575C41008148 @default.
- W3167277575 hasConceptScore W3167277575C50644808 @default.
- W3167277575 hasConceptScore W3167277575C89600930 @default.
- W3167277575 hasFunder F4320321001 @default.
- W3167277575 hasLocation W31672775751 @default.
- W3167277575 hasOpenAccess W3167277575 @default.
- W3167277575 hasPrimaryLocation W31672775751 @default.
- W3167277575 hasRelatedWork W1669643531 @default.
- W3167277575 hasRelatedWork W1963494852 @default.
- W3167277575 hasRelatedWork W2004370856 @default.
- W3167277575 hasRelatedWork W2019566805 @default.
- W3167277575 hasRelatedWork W2026019026 @default.
- W3167277575 hasRelatedWork W2101128524 @default.
- W3167277575 hasRelatedWork W2122581818 @default.
- W3167277575 hasRelatedWork W2383464976 @default.
- W3167277575 hasRelatedWork W2948658236 @default.
- W3167277575 hasRelatedWork W1967061043 @default.
- W3167277575 isParatext "false" @default.
- W3167277575 isRetracted "false" @default.
- W3167277575 magId "3167277575" @default.
- W3167277575 workType "article" @default.