Matches in SemOpenAlex for { <https://semopenalex.org/work/W2770180314> ?p ?o ?g. }
- W2770180314 abstract "While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this paper, we revisit the problem of purely unsupervised image segmentation and propose a novel deep architecture for this problem. We borrow recent ideas from supervised semantic segmentation methods, in particular by concatenating two fully convolutional networks together into an autoencoder--one for encoding and one for decoding. The encoding layer produces a k-way pixelwise prediction, and both the reconstruction error of the autoencoder as well as the normalized cut produced by the encoder are jointly minimized during training. When combined with suitable postprocessing involving conditional random field smoothing and hierarchical segmentation, our resulting algorithm achieves impressive results on the benchmark Berkeley Segmentation Data Set, outperforming a number of competing methods." @default.
- W2770180314 created "2017-12-04" @default.
- W2770180314 creator A5049134079 @default.
- W2770180314 creator A5091179204 @default.
- W2770180314 date "2017-11-22" @default.
- W2770180314 modified "2023-09-22" @default.
- W2770180314 title "W-Net: A Deep Model for Fully Unsupervised Image Segmentation" @default.
- W2770180314 cites W1901129140 @default.
- W2770180314 cites W1903029394 @default.
- W2770180314 cites W1923115158 @default.
- W2770180314 cites W1938976761 @default.
- W2770180314 cites W1948751323 @default.
- W2770180314 cites W2058871925 @default.
- W2770180314 cites W2097323414 @default.
- W2770180314 cites W2100495367 @default.
- W2770180314 cites W2116046277 @default.
- W2770180314 cites W2118558214 @default.
- W2770180314 cites W2139427956 @default.
- W2770180314 cites W2161236525 @default.
- W2770180314 cites W2412782625 @default.
- W2770180314 cites W2419448466 @default.
- W2770180314 cites W2949117887 @default.
- W2770180314 cites W2950612966 @default.
- W2770180314 cites W2951583185 @default.
- W2770180314 cites W2952637581 @default.
- W2770180314 cites W2963881378 @default.
- W2770180314 hasPublicationYear "2017" @default.
- W2770180314 type Work @default.
- W2770180314 sameAs 2770180314 @default.
- W2770180314 citedByCount "42" @default.
- W2770180314 countsByYear W27701803142018 @default.
- W2770180314 countsByYear W27701803142019 @default.
- W2770180314 countsByYear W27701803142020 @default.
- W2770180314 countsByYear W27701803142021 @default.
- W2770180314 crossrefType "posted-content" @default.
- W2770180314 hasAuthorship W2770180314A5049134079 @default.
- W2770180314 hasAuthorship W2770180314A5091179204 @default.
- W2770180314 hasConcept C101738243 @default.
- W2770180314 hasConcept C108583219 @default.
- W2770180314 hasConcept C111919701 @default.
- W2770180314 hasConcept C11413529 @default.
- W2770180314 hasConcept C118505674 @default.
- W2770180314 hasConcept C124504099 @default.
- W2770180314 hasConcept C125411270 @default.
- W2770180314 hasConcept C13280743 @default.
- W2770180314 hasConcept C152565575 @default.
- W2770180314 hasConcept C153180895 @default.
- W2770180314 hasConcept C154945302 @default.
- W2770180314 hasConcept C185798385 @default.
- W2770180314 hasConcept C205649164 @default.
- W2770180314 hasConcept C31972630 @default.
- W2770180314 hasConcept C3770464 @default.
- W2770180314 hasConcept C41008148 @default.
- W2770180314 hasConcept C57273362 @default.
- W2770180314 hasConcept C65885262 @default.
- W2770180314 hasConcept C89600930 @default.
- W2770180314 hasConceptScore W2770180314C101738243 @default.
- W2770180314 hasConceptScore W2770180314C108583219 @default.
- W2770180314 hasConceptScore W2770180314C111919701 @default.
- W2770180314 hasConceptScore W2770180314C11413529 @default.
- W2770180314 hasConceptScore W2770180314C118505674 @default.
- W2770180314 hasConceptScore W2770180314C124504099 @default.
- W2770180314 hasConceptScore W2770180314C125411270 @default.
- W2770180314 hasConceptScore W2770180314C13280743 @default.
- W2770180314 hasConceptScore W2770180314C152565575 @default.
- W2770180314 hasConceptScore W2770180314C153180895 @default.
- W2770180314 hasConceptScore W2770180314C154945302 @default.
- W2770180314 hasConceptScore W2770180314C185798385 @default.
- W2770180314 hasConceptScore W2770180314C205649164 @default.
- W2770180314 hasConceptScore W2770180314C31972630 @default.
- W2770180314 hasConceptScore W2770180314C3770464 @default.
- W2770180314 hasConceptScore W2770180314C41008148 @default.
- W2770180314 hasConceptScore W2770180314C57273362 @default.
- W2770180314 hasConceptScore W2770180314C65885262 @default.
- W2770180314 hasConceptScore W2770180314C89600930 @default.
- W2770180314 hasLocation W27701803141 @default.
- W2770180314 hasOpenAccess W2770180314 @default.
- W2770180314 hasPrimaryLocation W27701803141 @default.
- W2770180314 hasRelatedWork W1686810756 @default.
- W2770180314 hasRelatedWork W1861492603 @default.
- W2770180314 hasRelatedWork W1901129140 @default.
- W2770180314 hasRelatedWork W1903029394 @default.
- W2770180314 hasRelatedWork W1999478155 @default.
- W2770180314 hasRelatedWork W2067191022 @default.
- W2770180314 hasRelatedWork W2099471712 @default.
- W2770180314 hasRelatedWork W2102605133 @default.
- W2770180314 hasRelatedWork W2110158442 @default.
- W2770180314 hasRelatedWork W2118246710 @default.
- W2770180314 hasRelatedWork W2121947440 @default.
- W2770180314 hasRelatedWork W2163605009 @default.
- W2770180314 hasRelatedWork W2194775991 @default.
- W2770180314 hasRelatedWork W2412782625 @default.
- W2770180314 hasRelatedWork W2419448466 @default.
- W2770180314 hasRelatedWork W2560023338 @default.
- W2770180314 hasRelatedWork W2798122215 @default.
- W2770180314 hasRelatedWork W2801780873 @default.
- W2770180314 hasRelatedWork W2963881378 @default.
- W2770180314 hasRelatedWork W2964121744 @default.
- W2770180314 isParatext "false" @default.
- W2770180314 isRetracted "false" @default.