Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890995532> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W2890995532 abstract "Semantic segmentation plays an important role in a series of high-level computer vision applications. However, the performance of Convolutional Neural Network (CNN) based segmentation models is currently influenced by higher order inconsistencies, which are mainly caused by the CNNs built-in invariance to spatial transformations and the independent prediction for each of pixel. In this paper, a novel framework, consisting of a segmentation network and a Generative Adversarial Network (GAN), is proposed to tackle this challenging problem by enforcing long-range spatial label contiguity. With the help of fully connected layers in the discriminator and adversarial training, the GAN model can evaluate the higher-order potentials loss. The motivation is that the GAN model provides an auxiliary higher-order potentials loss to the segmentation model, thus the segmentation model have the ability of correcting higher order inconsistencies. Extensive experiments on public benchmarking database demonstrate the effectiveness of the proposed method." @default.
- W2890995532 created "2018-09-27" @default.
- W2890995532 creator A5003131468 @default.
- W2890995532 creator A5026853565 @default.
- W2890995532 creator A5029851897 @default.
- W2890995532 creator A5038835366 @default.
- W2890995532 creator A5073216396 @default.
- W2890995532 creator A5078514263 @default.
- W2890995532 date "2018-08-17" @default.
- W2890995532 modified "2023-10-18" @default.
- W2890995532 title "A novel framework for semantic segmentation with generative adversarial network" @default.
- W2890995532 cites W1745334888 @default.
- W2890995532 cites W1903029394 @default.
- W2890995532 cites W2037227137 @default.
- W2890995532 cites W2124592697 @default.
- W2890995532 cites W2340897893 @default.
- W2890995532 cites W2737312250 @default.
- W2890995532 cites W2963108253 @default.
- W2890995532 doi "https://doi.org/10.1145/3240876.3240891" @default.
- W2890995532 hasPublicationYear "2018" @default.
- W2890995532 type Work @default.
- W2890995532 sameAs 2890995532 @default.
- W2890995532 citedByCount "1" @default.
- W2890995532 countsByYear W28909955322019 @default.
- W2890995532 crossrefType "proceedings-article" @default.
- W2890995532 hasAuthorship W2890995532A5003131468 @default.
- W2890995532 hasAuthorship W2890995532A5026853565 @default.
- W2890995532 hasAuthorship W2890995532A5029851897 @default.
- W2890995532 hasAuthorship W2890995532A5038835366 @default.
- W2890995532 hasAuthorship W2890995532A5073216396 @default.
- W2890995532 hasAuthorship W2890995532A5078514263 @default.
- W2890995532 hasConcept C108583219 @default.
- W2890995532 hasConcept C154945302 @default.
- W2890995532 hasConcept C204321447 @default.
- W2890995532 hasConcept C2988773926 @default.
- W2890995532 hasConcept C37736160 @default.
- W2890995532 hasConcept C39890363 @default.
- W2890995532 hasConcept C41008148 @default.
- W2890995532 hasConcept C89600930 @default.
- W2890995532 hasConceptScore W2890995532C108583219 @default.
- W2890995532 hasConceptScore W2890995532C154945302 @default.
- W2890995532 hasConceptScore W2890995532C204321447 @default.
- W2890995532 hasConceptScore W2890995532C2988773926 @default.
- W2890995532 hasConceptScore W2890995532C37736160 @default.
- W2890995532 hasConceptScore W2890995532C39890363 @default.
- W2890995532 hasConceptScore W2890995532C41008148 @default.
- W2890995532 hasConceptScore W2890995532C89600930 @default.
- W2890995532 hasLocation W28909955321 @default.
- W2890995532 hasOpenAccess W2890995532 @default.
- W2890995532 hasPrimaryLocation W28909955321 @default.
- W2890995532 hasRelatedWork W2901368259 @default.
- W2890995532 hasRelatedWork W2998996837 @default.
- W2890995532 hasRelatedWork W3017161950 @default.
- W2890995532 hasRelatedWork W3024390022 @default.
- W2890995532 hasRelatedWork W3156291593 @default.
- W2890995532 hasRelatedWork W3164279787 @default.
- W2890995532 hasRelatedWork W4296176982 @default.
- W2890995532 hasRelatedWork W4311460979 @default.
- W2890995532 hasRelatedWork W4313479464 @default.
- W2890995532 hasRelatedWork W4316035501 @default.
- W2890995532 isParatext "false" @default.
- W2890995532 isRetracted "false" @default.
- W2890995532 magId "2890995532" @default.
- W2890995532 workType "article" @default.