Matches in SemOpenAlex for { <https://semopenalex.org/work/W2606129492> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2606129492 abstract "We propose a weakly supervised semantic segmentation algorithm that uses image tags for supervision. We apply the tags in queries to collect three sets of web images, which encode the clean foregrounds, the common backgrounds, and realistic scenes of the classes. We introduce a novel three-stage training pipeline to progressively learn semantic segmentation models. We first train and refine a class-specific shallow neural network to obtain segmentation masks for each class. The shallow neural networks of all classes are then assembled into one deep convolutional neural network for end-to-end training and testing. Experiments show that our method notably outperforms previous state-of-the-art weakly supervised semantic segmentation approaches on the PASCAL VOC 2012 segmentation benchmark. We further apply the class-specific shallow neural networks to object segmentation and obtain excellent results." @default.
- W2606129492 created "2017-04-28" @default.
- W2606129492 creator A5002342351 @default.
- W2606129492 creator A5016501019 @default.
- W2606129492 creator A5078201467 @default.
- W2606129492 date "2017-07-01" @default.
- W2606129492 modified "2023-10-16" @default.
- W2606129492 title "Webly Supervised Semantic Segmentation" @default.
- W2606129492 cites W1495267108 @default.
- W2606129492 cites W1745334888 @default.
- W2606129492 cites W1783315696 @default.
- W2606129492 cites W1903029394 @default.
- W2606129492 cites W1945608308 @default.
- W2606129492 cites W1963920598 @default.
- W2606129492 cites W1991367009 @default.
- W2606129492 cites W1996140089 @default.
- W2606129492 cites W2002754212 @default.
- W2606129492 cites W2031489346 @default.
- W2606129492 cites W2039313011 @default.
- W2606129492 cites W2050952849 @default.
- W2606129492 cites W2086052791 @default.
- W2606129492 cites W2117539524 @default.
- W2606129492 cites W2124219775 @default.
- W2606129492 cites W2124592697 @default.
- W2606129492 cites W2127292559 @default.
- W2606129492 cites W2144794286 @default.
- W2606129492 cites W2155893237 @default.
- W2606129492 cites W2203062554 @default.
- W2606129492 cites W2221898772 @default.
- W2606129492 cites W2266390837 @default.
- W2606129492 cites W2291422229 @default.
- W2606129492 cites W2520746254 @default.
- W2606129492 cites W2963563573 @default.
- W2606129492 cites W2963873508 @default.
- W2606129492 doi "https://doi.org/10.1109/cvpr.2017.185" @default.
- W2606129492 hasPublicationYear "2017" @default.
- W2606129492 type Work @default.
- W2606129492 sameAs 2606129492 @default.
- W2606129492 citedByCount "68" @default.
- W2606129492 countsByYear W26061294922017 @default.
- W2606129492 countsByYear W26061294922018 @default.
- W2606129492 countsByYear W26061294922019 @default.
- W2606129492 countsByYear W26061294922020 @default.
- W2606129492 countsByYear W26061294922021 @default.
- W2606129492 countsByYear W26061294922022 @default.
- W2606129492 countsByYear W26061294922023 @default.
- W2606129492 crossrefType "proceedings-article" @default.
- W2606129492 hasAuthorship W2606129492A5002342351 @default.
- W2606129492 hasAuthorship W2606129492A5016501019 @default.
- W2606129492 hasAuthorship W2606129492A5078201467 @default.
- W2606129492 hasBestOaLocation W26061294922 @default.
- W2606129492 hasConcept C119857082 @default.
- W2606129492 hasConcept C124504099 @default.
- W2606129492 hasConcept C153180895 @default.
- W2606129492 hasConcept C154945302 @default.
- W2606129492 hasConcept C185798385 @default.
- W2606129492 hasConcept C199360897 @default.
- W2606129492 hasConcept C205649164 @default.
- W2606129492 hasConcept C2777212361 @default.
- W2606129492 hasConcept C41008148 @default.
- W2606129492 hasConcept C43521106 @default.
- W2606129492 hasConcept C50644808 @default.
- W2606129492 hasConcept C58640448 @default.
- W2606129492 hasConcept C75608658 @default.
- W2606129492 hasConcept C81363708 @default.
- W2606129492 hasConcept C89600930 @default.
- W2606129492 hasConceptScore W2606129492C119857082 @default.
- W2606129492 hasConceptScore W2606129492C124504099 @default.
- W2606129492 hasConceptScore W2606129492C153180895 @default.
- W2606129492 hasConceptScore W2606129492C154945302 @default.
- W2606129492 hasConceptScore W2606129492C185798385 @default.
- W2606129492 hasConceptScore W2606129492C199360897 @default.
- W2606129492 hasConceptScore W2606129492C205649164 @default.
- W2606129492 hasConceptScore W2606129492C2777212361 @default.
- W2606129492 hasConceptScore W2606129492C41008148 @default.
- W2606129492 hasConceptScore W2606129492C43521106 @default.
- W2606129492 hasConceptScore W2606129492C50644808 @default.
- W2606129492 hasConceptScore W2606129492C58640448 @default.
- W2606129492 hasConceptScore W2606129492C75608658 @default.
- W2606129492 hasConceptScore W2606129492C81363708 @default.
- W2606129492 hasConceptScore W2606129492C89600930 @default.
- W2606129492 hasLocation W26061294921 @default.
- W2606129492 hasLocation W26061294922 @default.
- W2606129492 hasOpenAccess W2606129492 @default.
- W2606129492 hasPrimaryLocation W26061294921 @default.
- W2606129492 hasRelatedWork W2424871898 @default.
- W2606129492 hasRelatedWork W2767651786 @default.
- W2606129492 hasRelatedWork W2912288872 @default.
- W2606129492 hasRelatedWork W2952466432 @default.
- W2606129492 hasRelatedWork W3021430260 @default.
- W2606129492 hasRelatedWork W3027997911 @default.
- W2606129492 hasRelatedWork W3049644159 @default.
- W2606129492 hasRelatedWork W4200528772 @default.
- W2606129492 hasRelatedWork W4287776258 @default.
- W2606129492 hasRelatedWork W4297914674 @default.
- W2606129492 isParatext "false" @default.
- W2606129492 isRetracted "false" @default.
- W2606129492 magId "2606129492" @default.
- W2606129492 workType "article" @default.