Matches in SemOpenAlex for { <https://semopenalex.org/work/W2215086518> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2215086518 endingPage "1895" @default.
- W2215086518 startingPage "1889" @default.
- W2215086518 abstract "We propose a novel approach to semantic segmentation using weakly supervised labels. In traditional fully supervised methods, superpixel labels are available for training; however, it is not easy to obtain enough labeled superpixels to learn a satisfying model for semantic segmentation. By contrast, only image-level labels are necessary in weakly supervised methods, which makes them more practical in real applications. In this paper we develop a new way of evaluating classification models for semantic segmentation given weekly supervised labels. For a certain category, provided the classification model parameter, we firstly learn the basis superpixels by sparse reconstruction, and then evaluate the parameters by measuring the reconstruction errors among negative and positive superpixels. Based on Gaussian Mixture Models, we use Iterative Merging Update (IMU) algorithm to obtain the best parameters for the classification models. Experimental results on two real-world datasets show that the proposed approach outperforms the existing weakly supervised methods, and it also competes with state-of-the-art fully supervised methods." @default.
- W2215086518 created "2016-06-24" @default.
- W2215086518 creator A5003418019 @default.
- W2215086518 creator A5030064573 @default.
- W2215086518 creator A5041717877 @default.
- W2215086518 creator A5056833841 @default.
- W2215086518 date "2013-08-03" @default.
- W2215086518 modified "2023-10-03" @default.
- W2215086518 title "Sparse reconstruction for weakly supervised semantic segmentation" @default.
- W2215086518 cites W1492409332 @default.
- W2215086518 cites W1495965410 @default.
- W2215086518 cites W1528789833 @default.
- W2215086518 cites W157583248 @default.
- W2215086518 cites W1581592866 @default.
- W2215086518 cites W1666447063 @default.
- W2215086518 cites W1736339626 @default.
- W2215086518 cites W1748750709 @default.
- W2215086518 cites W1994259434 @default.
- W2215086518 cites W2003217181 @default.
- W2215086518 cites W2026581312 @default.
- W2215086518 cites W2029731618 @default.
- W2215086518 cites W2037227137 @default.
- W2215086518 cites W2039461297 @default.
- W2215086518 cites W2067191022 @default.
- W2215086518 cites W2083053289 @default.
- W2215086518 cites W2100247797 @default.
- W2215086518 cites W2100588357 @default.
- W2215086518 cites W2116877738 @default.
- W2215086518 cites W2123023145 @default.
- W2215086518 cites W2149954907 @default.
- W2215086518 cites W2151103935 @default.
- W2215086518 cites W2158427031 @default.
- W2215086518 cites W2535516436 @default.
- W2215086518 cites W70785481 @default.
- W2215086518 cites W79405465 @default.
- W2215086518 hasPublicationYear "2013" @default.
- W2215086518 type Work @default.
- W2215086518 sameAs 2215086518 @default.
- W2215086518 citedByCount "8" @default.
- W2215086518 countsByYear W22150865182014 @default.
- W2215086518 countsByYear W22150865182015 @default.
- W2215086518 countsByYear W22150865182018 @default.
- W2215086518 crossrefType "proceedings-article" @default.
- W2215086518 hasAuthorship W2215086518A5003418019 @default.
- W2215086518 hasAuthorship W2215086518A5030064573 @default.
- W2215086518 hasAuthorship W2215086518A5041717877 @default.
- W2215086518 hasAuthorship W2215086518A5056833841 @default.
- W2215086518 hasConcept C119857082 @default.
- W2215086518 hasConcept C124504099 @default.
- W2215086518 hasConcept C136389625 @default.
- W2215086518 hasConcept C153180895 @default.
- W2215086518 hasConcept C154945302 @default.
- W2215086518 hasConcept C41008148 @default.
- W2215086518 hasConcept C50644808 @default.
- W2215086518 hasConcept C89600930 @default.
- W2215086518 hasConceptScore W2215086518C119857082 @default.
- W2215086518 hasConceptScore W2215086518C124504099 @default.
- W2215086518 hasConceptScore W2215086518C136389625 @default.
- W2215086518 hasConceptScore W2215086518C153180895 @default.
- W2215086518 hasConceptScore W2215086518C154945302 @default.
- W2215086518 hasConceptScore W2215086518C41008148 @default.
- W2215086518 hasConceptScore W2215086518C50644808 @default.
- W2215086518 hasConceptScore W2215086518C89600930 @default.
- W2215086518 hasLocation W22150865181 @default.
- W2215086518 hasOpenAccess W2215086518 @default.
- W2215086518 hasPrimaryLocation W22150865181 @default.
- W2215086518 hasRelatedWork W1528789833 @default.
- W2215086518 hasRelatedWork W1748750709 @default.
- W2215086518 hasRelatedWork W1901229278 @default.
- W2215086518 hasRelatedWork W1903029394 @default.
- W2215086518 hasRelatedWork W1983521647 @default.
- W2215086518 hasRelatedWork W2026581312 @default.
- W2215086518 hasRelatedWork W2029731618 @default.
- W2215086518 hasRelatedWork W2031489346 @default.
- W2215086518 hasRelatedWork W2049612634 @default.
- W2215086518 hasRelatedWork W2100588357 @default.
- W2215086518 hasRelatedWork W2118246710 @default.
- W2215086518 hasRelatedWork W2123023145 @default.
- W2215086518 hasRelatedWork W2125849446 @default.
- W2215086518 hasRelatedWork W2158305599 @default.
- W2215086518 hasRelatedWork W2158427031 @default.
- W2215086518 hasRelatedWork W2535516436 @default.
- W2215086518 hasRelatedWork W3090212082 @default.
- W2215086518 hasRelatedWork W3130223701 @default.
- W2215086518 hasRelatedWork W3147929628 @default.
- W2215086518 hasRelatedWork W3177450673 @default.
- W2215086518 isParatext "false" @default.
- W2215086518 isRetracted "false" @default.
- W2215086518 magId "2215086518" @default.
- W2215086518 workType "article" @default.