Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949086864> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2949086864 abstract "Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the performance of deep networks that usually benefit from more training data. In this paper, we propose a method that achieves competitive accuracy but only requires easily obtained bounding box annotations. The basic idea is to iterate between automatically generating region proposals and training convolutional networks. These two steps gradually recover segmentation masks for improving the networks, and vise versa. Our method, called BoxSup, produces competitive results supervised by boxes only, on par with strong baselines fully supervised by masks under the same setting. By leveraging a large amount of bounding boxes, BoxSup further unleashes the power of deep convolutional networks and yields state-of-the-art results on PASCAL VOC 2012 and PASCAL-CONTEXT." @default.
- W2949086864 created "2019-06-27" @default.
- W2949086864 creator A5004183775 @default.
- W2949086864 creator A5026944066 @default.
- W2949086864 creator A5049098969 @default.
- W2949086864 date "2015-03-05" @default.
- W2949086864 modified "2023-09-25" @default.
- W2949086864 title "BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation" @default.
- W2949086864 cites W1497265063 @default.
- W2949086864 cites W1529410181 @default.
- W2949086864 cites W1659581753 @default.
- W2949086864 cites W1677182931 @default.
- W2949086864 cites W1861492603 @default.
- W2949086864 cites W1903029394 @default.
- W2949086864 cites W1923115158 @default.
- W2949086864 cites W1948751323 @default.
- W2949086864 cites W1991367009 @default.
- W2949086864 cites W1994002998 @default.
- W2949086864 cites W2031489346 @default.
- W2949086864 cites W2088049833 @default.
- W2949086864 cites W2097117768 @default.
- W2949086864 cites W2102605133 @default.
- W2949086864 cites W2108598243 @default.
- W2949086864 cites W2116877738 @default.
- W2949086864 cites W2117741877 @default.
- W2949086864 cites W2124351162 @default.
- W2949086864 cites W2125215748 @default.
- W2949086864 cites W2127194945 @default.
- W2949086864 cites W2144794286 @default.
- W2949086864 cites W2147800946 @default.
- W2949086864 cites W2206858481 @default.
- W2949086864 cites W261873710 @default.
- W2949086864 cites W2949511860 @default.
- W2949086864 cites W2952020226 @default.
- W2949086864 cites W2952029950 @default.
- W2949086864 cites W2962835968 @default.
- W2949086864 cites W2963542991 @default.
- W2949086864 cites W2964288706 @default.
- W2949086864 cites W78159342 @default.
- W2949086864 doi "https://doi.org/10.48550/arxiv.1503.01640" @default.
- W2949086864 hasPublicationYear "2015" @default.
- W2949086864 type Work @default.
- W2949086864 sameAs 2949086864 @default.
- W2949086864 citedByCount "105" @default.
- W2949086864 countsByYear W29490868642015 @default.
- W2949086864 countsByYear W29490868642016 @default.
- W2949086864 countsByYear W29490868642017 @default.
- W2949086864 countsByYear W29490868642018 @default.
- W2949086864 countsByYear W29490868642019 @default.
- W2949086864 countsByYear W29490868642020 @default.
- W2949086864 countsByYear W29490868642021 @default.
- W2949086864 crossrefType "posted-content" @default.
- W2949086864 hasAuthorship W2949086864A5004183775 @default.
- W2949086864 hasAuthorship W2949086864A5026944066 @default.
- W2949086864 hasAuthorship W2949086864A5049098969 @default.
- W2949086864 hasBestOaLocation W29490868641 @default.
- W2949086864 hasConcept C108583219 @default.
- W2949086864 hasConcept C115961682 @default.
- W2949086864 hasConcept C119857082 @default.
- W2949086864 hasConcept C147037132 @default.
- W2949086864 hasConcept C153180895 @default.
- W2949086864 hasConcept C154945302 @default.
- W2949086864 hasConcept C160633673 @default.
- W2949086864 hasConcept C199360897 @default.
- W2949086864 hasConcept C41008148 @default.
- W2949086864 hasConcept C63584917 @default.
- W2949086864 hasConcept C75608658 @default.
- W2949086864 hasConcept C81363708 @default.
- W2949086864 hasConcept C89600930 @default.
- W2949086864 hasConceptScore W2949086864C108583219 @default.
- W2949086864 hasConceptScore W2949086864C115961682 @default.
- W2949086864 hasConceptScore W2949086864C119857082 @default.
- W2949086864 hasConceptScore W2949086864C147037132 @default.
- W2949086864 hasConceptScore W2949086864C153180895 @default.
- W2949086864 hasConceptScore W2949086864C154945302 @default.
- W2949086864 hasConceptScore W2949086864C160633673 @default.
- W2949086864 hasConceptScore W2949086864C199360897 @default.
- W2949086864 hasConceptScore W2949086864C41008148 @default.
- W2949086864 hasConceptScore W2949086864C63584917 @default.
- W2949086864 hasConceptScore W2949086864C75608658 @default.
- W2949086864 hasConceptScore W2949086864C81363708 @default.
- W2949086864 hasConceptScore W2949086864C89600930 @default.
- W2949086864 hasLocation W29490868641 @default.
- W2949086864 hasOpenAccess W2949086864 @default.
- W2949086864 hasPrimaryLocation W29490868641 @default.
- W2949086864 hasRelatedWork W1495267108 @default.
- W2949086864 hasRelatedWork W2769769732 @default.
- W2949086864 hasRelatedWork W2949086864 @default.
- W2949086864 hasRelatedWork W2965095255 @default.
- W2949086864 hasRelatedWork W3102253946 @default.
- W2949086864 hasRelatedWork W3194889229 @default.
- W2949086864 hasRelatedWork W3214521593 @default.
- W2949086864 hasRelatedWork W4224223242 @default.
- W2949086864 hasRelatedWork W4293211451 @default.
- W2949086864 hasRelatedWork W4313854567 @default.
- W2949086864 isParatext "false" @default.
- W2949086864 isRetracted "false" @default.
- W2949086864 magId "2949086864" @default.
- W2949086864 workType "article" @default.