Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765143375> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2765143375 abstract "Image recognition tasks that involve identifying parts of an object or the contents of a vessel can be viewed as a hierarchical problem, which can be solved by initial recognition of the main object, followed by recognition of its parts or contents. To achieve such modular recognition, it is necessary to use the output of one recognition method (which identifies the general object) as the input for a second method (which identifies the parts or contents). In recent years, convolutional neural networks have emerged as the dominant method for segmentation and classification of images. This work examines a method for serially connecting convolutional neural networks for semantic segmentation of materials inside transparent vessels. It applies one fully convolutional neural net to segment the image into vessel and background, and the vessel region is used as an input for a second net which recognizes the contents of the glass vessel. Transferring the segmentation map generated by the first nets to the second net was performed using the valve filter attention method that involves using different filters on different segments of the image. This modular semantic segmentation method outperforms a single step method in which both the vessel and its contents are identified using a single net. An advantage of the modular neural net is that it allows networks to be built from existing trained modules, as well the transfer and reuse of trained net modules without the need for any retraining of the assembled net." @default.
- W2765143375 created "2017-11-10" @default.
- W2765143375 creator A5021796022 @default.
- W2765143375 date "2017-10-14" @default.
- W2765143375 modified "2023-09-27" @default.
- W2765143375 title "Hierarchical semantic segmentation using modular convolutional neural networks." @default.
- W2765143375 cites W1903029394 @default.
- W2765143375 cites W194410883 @default.
- W2765143375 cites W1998751443 @default.
- W2765143375 cites W2013825418 @default.
- W2765143375 cites W2045257906 @default.
- W2765143375 cites W2131391163 @default.
- W2765143375 cites W2149194912 @default.
- W2765143375 cites W2174492417 @default.
- W2765143375 cites W2272931141 @default.
- W2765143375 cites W2284813959 @default.
- W2765143375 cites W2304648132 @default.
- W2765143375 cites W2399004904 @default.
- W2765143375 cites W2412782625 @default.
- W2765143375 cites W2579318141 @default.
- W2765143375 cites W2583761661 @default.
- W2765143375 cites W2609077090 @default.
- W2765143375 cites W2751119241 @default.
- W2765143375 cites W2949341804 @default.
- W2765143375 cites W2950015165 @default.
- W2765143375 cites W2950053619 @default.
- W2765143375 cites W2950107101 @default.
- W2765143375 cites W2950725920 @default.
- W2765143375 cites W2951275671 @default.
- W2765143375 cites W2951329458 @default.
- W2765143375 cites W2952339051 @default.
- W2765143375 cites W2952375731 @default.
- W2765143375 cites W2963191264 @default.
- W2765143375 cites W2963203586 @default.
- W2765143375 cites W2963881378 @default.
- W2765143375 cites W933663465 @default.
- W2765143375 hasPublicationYear "2017" @default.
- W2765143375 type Work @default.
- W2765143375 sameAs 2765143375 @default.
- W2765143375 citedByCount "2" @default.
- W2765143375 countsByYear W27651433752018 @default.
- W2765143375 countsByYear W27651433752021 @default.
- W2765143375 crossrefType "posted-content" @default.
- W2765143375 hasAuthorship W2765143375A5021796022 @default.
- W2765143375 hasConcept C101468663 @default.
- W2765143375 hasConcept C106131492 @default.
- W2765143375 hasConcept C111919701 @default.
- W2765143375 hasConcept C153180895 @default.
- W2765143375 hasConcept C154945302 @default.
- W2765143375 hasConcept C175202392 @default.
- W2765143375 hasConcept C2781121602 @default.
- W2765143375 hasConcept C2781238097 @default.
- W2765143375 hasConcept C31972630 @default.
- W2765143375 hasConcept C41008148 @default.
- W2765143375 hasConcept C50644808 @default.
- W2765143375 hasConcept C81363708 @default.
- W2765143375 hasConcept C89600930 @default.
- W2765143375 hasConceptScore W2765143375C101468663 @default.
- W2765143375 hasConceptScore W2765143375C106131492 @default.
- W2765143375 hasConceptScore W2765143375C111919701 @default.
- W2765143375 hasConceptScore W2765143375C153180895 @default.
- W2765143375 hasConceptScore W2765143375C154945302 @default.
- W2765143375 hasConceptScore W2765143375C175202392 @default.
- W2765143375 hasConceptScore W2765143375C2781121602 @default.
- W2765143375 hasConceptScore W2765143375C2781238097 @default.
- W2765143375 hasConceptScore W2765143375C31972630 @default.
- W2765143375 hasConceptScore W2765143375C41008148 @default.
- W2765143375 hasConceptScore W2765143375C50644808 @default.
- W2765143375 hasConceptScore W2765143375C81363708 @default.
- W2765143375 hasConceptScore W2765143375C89600930 @default.
- W2765143375 hasLocation W27651433751 @default.
- W2765143375 hasOpenAccess W2765143375 @default.
- W2765143375 hasPrimaryLocation W27651433751 @default.
- W2765143375 hasRelatedWork W2175578667 @default.
- W2765143375 hasRelatedWork W2920913251 @default.
- W2765143375 hasRelatedWork W2963455537 @default.
- W2765143375 hasRelatedWork W3105789036 @default.
- W2765143375 hasRelatedWork W2930754807 @default.
- W2765143375 hasRelatedWork W2960564149 @default.
- W2765143375 hasRelatedWork W2968588090 @default.
- W2765143375 hasRelatedWork W2983498673 @default.
- W2765143375 hasRelatedWork W2993029403 @default.
- W2765143375 hasRelatedWork W3001726715 @default.
- W2765143375 hasRelatedWork W3002308053 @default.
- W2765143375 hasRelatedWork W3002753099 @default.
- W2765143375 hasRelatedWork W3002778397 @default.
- W2765143375 hasRelatedWork W3020462618 @default.
- W2765143375 hasRelatedWork W3038666428 @default.
- W2765143375 hasRelatedWork W3070917989 @default.
- W2765143375 hasRelatedWork W3072373137 @default.
- W2765143375 hasRelatedWork W3076199500 @default.
- W2765143375 hasRelatedWork W3090585167 @default.
- W2765143375 hasRelatedWork W3109770907 @default.
- W2765143375 isParatext "false" @default.
- W2765143375 isRetracted "false" @default.
- W2765143375 magId "2765143375" @default.
- W2765143375 workType "article" @default.