Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891385666> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2891385666 abstract "This paper presents a deep learning approach to Kaggle Carvana Image Masking Competition, which aims at extracting the car objects in high quality images with the background removed. We formulate the background extraction problem as an image segmentation problem. In this challenge, we have evaluated different U-Net architectures. We have explored two different techniques in combining encoder downsampling features with decoder upsampling features. In addition, we have experimented replacing different pre-trained networks to accelerate the training process. Finally, we have trained different models at different image scales and predicted the final result with the ensemble method. Our final method has placed us at top 4% in the challenge and achieved a dice coefficient score of 0.99694." @default.
- W2891385666 created "2018-09-27" @default.
- W2891385666 creator A5017188540 @default.
- W2891385666 creator A5035545617 @default.
- W2891385666 creator A5056666350 @default.
- W2891385666 creator A5070618832 @default.
- W2891385666 creator A5070624819 @default.
- W2891385666 date "2018-01-01" @default.
- W2891385666 modified "2023-09-24" @default.
- W2891385666 title "Removing Background with Semantic Segmentation Based on Ensemble Learning" @default.
- W2891385666 cites W1665214252 @default.
- W2891385666 cites W1686810756 @default.
- W2891385666 cites W1836465849 @default.
- W2891385666 cites W1901129140 @default.
- W2891385666 cites W1903029394 @default.
- W2891385666 cites W1910657905 @default.
- W2891385666 cites W2095844239 @default.
- W2891385666 cites W2097117768 @default.
- W2891385666 cites W2108598243 @default.
- W2891385666 cites W2149933564 @default.
- W2891385666 cites W2194775991 @default.
- W2891385666 cites W2274287116 @default.
- W2891385666 cites W2302255633 @default.
- W2891385666 cites W2563705555 @default.
- W2891385666 cites W2618530766 @default.
- W2891385666 cites W2919115771 @default.
- W2891385666 cites W2952865063 @default.
- W2891385666 doi "https://doi.org/10.4108/eai.21-6-2018.2276586" @default.
- W2891385666 hasPublicationYear "2018" @default.
- W2891385666 type Work @default.
- W2891385666 sameAs 2891385666 @default.
- W2891385666 citedByCount "0" @default.
- W2891385666 crossrefType "proceedings-article" @default.
- W2891385666 hasAuthorship W2891385666A5017188540 @default.
- W2891385666 hasAuthorship W2891385666A5035545617 @default.
- W2891385666 hasAuthorship W2891385666A5056666350 @default.
- W2891385666 hasAuthorship W2891385666A5070618832 @default.
- W2891385666 hasAuthorship W2891385666A5070624819 @default.
- W2891385666 hasBestOaLocation W28913856661 @default.
- W2891385666 hasConcept C108583219 @default.
- W2891385666 hasConcept C110384440 @default.
- W2891385666 hasConcept C111919701 @default.
- W2891385666 hasConcept C115961682 @default.
- W2891385666 hasConcept C118505674 @default.
- W2891385666 hasConcept C119857082 @default.
- W2891385666 hasConcept C124504099 @default.
- W2891385666 hasConcept C153180895 @default.
- W2891385666 hasConcept C154945302 @default.
- W2891385666 hasConcept C22029948 @default.
- W2891385666 hasConcept C2524010 @default.
- W2891385666 hasConcept C31972630 @default.
- W2891385666 hasConcept C33923547 @default.
- W2891385666 hasConcept C41008148 @default.
- W2891385666 hasConcept C89600930 @default.
- W2891385666 hasConceptScore W2891385666C108583219 @default.
- W2891385666 hasConceptScore W2891385666C110384440 @default.
- W2891385666 hasConceptScore W2891385666C111919701 @default.
- W2891385666 hasConceptScore W2891385666C115961682 @default.
- W2891385666 hasConceptScore W2891385666C118505674 @default.
- W2891385666 hasConceptScore W2891385666C119857082 @default.
- W2891385666 hasConceptScore W2891385666C124504099 @default.
- W2891385666 hasConceptScore W2891385666C153180895 @default.
- W2891385666 hasConceptScore W2891385666C154945302 @default.
- W2891385666 hasConceptScore W2891385666C22029948 @default.
- W2891385666 hasConceptScore W2891385666C2524010 @default.
- W2891385666 hasConceptScore W2891385666C31972630 @default.
- W2891385666 hasConceptScore W2891385666C33923547 @default.
- W2891385666 hasConceptScore W2891385666C41008148 @default.
- W2891385666 hasConceptScore W2891385666C89600930 @default.
- W2891385666 hasLocation W28913856661 @default.
- W2891385666 hasOpenAccess W2891385666 @default.
- W2891385666 hasPrimaryLocation W28913856661 @default.
- W2891385666 hasRelatedWork W134390715 @default.
- W2891385666 hasRelatedWork W1502765116 @default.
- W2891385666 hasRelatedWork W1945608308 @default.
- W2891385666 hasRelatedWork W2318872361 @default.
- W2891385666 hasRelatedWork W2530751448 @default.
- W2891385666 hasRelatedWork W2575253144 @default.
- W2891385666 hasRelatedWork W2773771410 @default.
- W2891385666 hasRelatedWork W2789255933 @default.
- W2891385666 hasRelatedWork W2907536214 @default.
- W2891385666 hasRelatedWork W2912237114 @default.
- W2891385666 hasRelatedWork W2953419979 @default.
- W2891385666 hasRelatedWork W2960325384 @default.
- W2891385666 hasRelatedWork W3026341053 @default.
- W2891385666 hasRelatedWork W3034520465 @default.
- W2891385666 hasRelatedWork W3122184312 @default.
- W2891385666 hasRelatedWork W3124338021 @default.
- W2891385666 hasRelatedWork W3125346278 @default.
- W2891385666 hasRelatedWork W3146991503 @default.
- W2891385666 hasRelatedWork W3197720259 @default.
- W2891385666 hasRelatedWork W3096003402 @default.
- W2891385666 isParatext "false" @default.
- W2891385666 isRetracted "false" @default.
- W2891385666 magId "2891385666" @default.
- W2891385666 workType "article" @default.