Matches in SemOpenAlex for { <https://semopenalex.org/work/W2029731618> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2029731618 abstract "We address the task of learning a semantic segmentation from weakly supervised data. Our aim is to devise a system that predicts an object label for each pixel by making use of only image level labels during training - the information whether a certain object is present or not in the image. Such coarse tagging of images is faster and easier to obtain as opposed to the tedious task of pixelwise labeling required in state of the art systems. We cast this task naturally as a multiple instance learning (MIL) problem. We use Semantic Texton Forest (STF) as the basic framework and extend it for the MIL setting. We make use of multitask learning (MTL) to regularize our solution. Here, an external task of geometric context estimation is used to improve on the task of semantic segmentation. We report experimental results on the MSRC21 and the very challenging VOC2007 datasets. On MSRC21 dataset we are able, by using 276 weakly labeled images, to achieve the performance of a supervised STF trained on pixelwise labeled training set of 56 images, which is a significant reduction in supervision needed." @default.
- W2029731618 created "2016-06-24" @default.
- W2029731618 creator A5019603588 @default.
- W2029731618 creator A5038199211 @default.
- W2029731618 date "2010-06-01" @default.
- W2029731618 modified "2023-10-03" @default.
- W2029731618 title "Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning" @default.
- W2029731618 cites W2100588357 @default.
- W2029731618 cites W2116133729 @default.
- W2029731618 cites W2123023145 @default.
- W2029731618 cites W2155871590 @default.
- W2029731618 doi "https://doi.org/10.1109/cvpr.2010.5540060" @default.
- W2029731618 hasPublicationYear "2010" @default.
- W2029731618 type Work @default.
- W2029731618 sameAs 2029731618 @default.
- W2029731618 citedByCount "121" @default.
- W2029731618 countsByYear W20297316182012 @default.
- W2029731618 countsByYear W20297316182013 @default.
- W2029731618 countsByYear W20297316182014 @default.
- W2029731618 countsByYear W20297316182015 @default.
- W2029731618 countsByYear W20297316182016 @default.
- W2029731618 countsByYear W20297316182017 @default.
- W2029731618 countsByYear W20297316182018 @default.
- W2029731618 countsByYear W20297316182019 @default.
- W2029731618 countsByYear W20297316182020 @default.
- W2029731618 countsByYear W20297316182021 @default.
- W2029731618 countsByYear W20297316182022 @default.
- W2029731618 countsByYear W20297316182023 @default.
- W2029731618 crossrefType "proceedings-article" @default.
- W2029731618 hasAuthorship W2029731618A5019603588 @default.
- W2029731618 hasAuthorship W2029731618A5038199211 @default.
- W2029731618 hasConcept C119857082 @default.
- W2029731618 hasConcept C124504099 @default.
- W2029731618 hasConcept C136389625 @default.
- W2029731618 hasConcept C151730666 @default.
- W2029731618 hasConcept C153180895 @default.
- W2029731618 hasConcept C154945302 @default.
- W2029731618 hasConcept C160633673 @default.
- W2029731618 hasConcept C162324750 @default.
- W2029731618 hasConcept C177264268 @default.
- W2029731618 hasConcept C184337299 @default.
- W2029731618 hasConcept C187736073 @default.
- W2029731618 hasConcept C199360897 @default.
- W2029731618 hasConcept C2779343474 @default.
- W2029731618 hasConcept C2780451532 @default.
- W2029731618 hasConcept C2781238097 @default.
- W2029731618 hasConcept C28006648 @default.
- W2029731618 hasConcept C41008148 @default.
- W2029731618 hasConcept C50644808 @default.
- W2029731618 hasConcept C51632099 @default.
- W2029731618 hasConcept C86803240 @default.
- W2029731618 hasConcept C89600930 @default.
- W2029731618 hasConceptScore W2029731618C119857082 @default.
- W2029731618 hasConceptScore W2029731618C124504099 @default.
- W2029731618 hasConceptScore W2029731618C136389625 @default.
- W2029731618 hasConceptScore W2029731618C151730666 @default.
- W2029731618 hasConceptScore W2029731618C153180895 @default.
- W2029731618 hasConceptScore W2029731618C154945302 @default.
- W2029731618 hasConceptScore W2029731618C160633673 @default.
- W2029731618 hasConceptScore W2029731618C162324750 @default.
- W2029731618 hasConceptScore W2029731618C177264268 @default.
- W2029731618 hasConceptScore W2029731618C184337299 @default.
- W2029731618 hasConceptScore W2029731618C187736073 @default.
- W2029731618 hasConceptScore W2029731618C199360897 @default.
- W2029731618 hasConceptScore W2029731618C2779343474 @default.
- W2029731618 hasConceptScore W2029731618C2780451532 @default.
- W2029731618 hasConceptScore W2029731618C2781238097 @default.
- W2029731618 hasConceptScore W2029731618C28006648 @default.
- W2029731618 hasConceptScore W2029731618C41008148 @default.
- W2029731618 hasConceptScore W2029731618C50644808 @default.
- W2029731618 hasConceptScore W2029731618C51632099 @default.
- W2029731618 hasConceptScore W2029731618C86803240 @default.
- W2029731618 hasConceptScore W2029731618C89600930 @default.
- W2029731618 hasLocation W20297316181 @default.
- W2029731618 hasOpenAccess W2029731618 @default.
- W2029731618 hasPrimaryLocation W20297316181 @default.
- W2029731618 hasRelatedWork W1987706094 @default.
- W2029731618 hasRelatedWork W2019566805 @default.
- W2029731618 hasRelatedWork W2136485282 @default.
- W2029731618 hasRelatedWork W2162802639 @default.
- W2029731618 hasRelatedWork W2546871836 @default.
- W2029731618 hasRelatedWork W2983785000 @default.
- W2029731618 hasRelatedWork W3161321444 @default.
- W2029731618 hasRelatedWork W4319309271 @default.
- W2029731618 hasRelatedWork W4385607619 @default.
- W2029731618 hasRelatedWork W1967061043 @default.
- W2029731618 isParatext "false" @default.
- W2029731618 isRetracted "false" @default.
- W2029731618 magId "2029731618" @default.
- W2029731618 workType "article" @default.