Matches in SemOpenAlex for { <https://semopenalex.org/work/W2788014765> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2788014765 abstract "In this work, we present a novel approach for training Generative Adversarial Networks (GANs). Using the attention maps produced by a Teacher- Network we are able to improve the quality of the generated images as well as perform weakly object localization on the generated images. To this end, we generate images of HEp-2 cells captured with Indirect Imunofluoresence (IIF) and study the ability of our network to perform a weakly localization of the cell. Firstly, we demonstrate that whilst GANs can learn the mapping between the input domain and the target distribution efficiently, the discriminator network is not able to detect the regions of interest. Secondly, we present a novel attention transfer mechanism which allows us to enforce the discriminator to put emphasis on the regions of interest via transfer learning. Thirdly, we show that this leads to more realistic images, as the discriminator learns to put emphasis on the area of interest. Fourthly, the proposed method allows one to generate both images as well as attention maps which can be useful for data annotation e.g in object detection." @default.
- W2788014765 created "2018-03-06" @default.
- W2788014765 creator A5004766028 @default.
- W2788014765 creator A5008187790 @default.
- W2788014765 creator A5041928666 @default.
- W2788014765 creator A5067738598 @default.
- W2788014765 creator A5080828884 @default.
- W2788014765 date "2018-02-25" @default.
- W2788014765 modified "2023-09-27" @default.
- W2788014765 title "Attention-Aware Generative Adversarial Networks (ATA-GANs)" @default.
- W2788014765 cites W1821462560 @default.
- W2788014765 cites W1994488211 @default.
- W2788014765 cites W2161381512 @default.
- W2788014765 cites W2279098554 @default.
- W2788014765 cites W1614862348 @default.
- W2788014765 hasPublicationYear "2018" @default.
- W2788014765 type Work @default.
- W2788014765 sameAs 2788014765 @default.
- W2788014765 citedByCount "7" @default.
- W2788014765 countsByYear W27880147652018 @default.
- W2788014765 countsByYear W27880147652019 @default.
- W2788014765 countsByYear W27880147652020 @default.
- W2788014765 countsByYear W27880147652021 @default.
- W2788014765 crossrefType "posted-content" @default.
- W2788014765 hasAuthorship W2788014765A5004766028 @default.
- W2788014765 hasAuthorship W2788014765A5008187790 @default.
- W2788014765 hasAuthorship W2788014765A5041928666 @default.
- W2788014765 hasAuthorship W2788014765A5067738598 @default.
- W2788014765 hasAuthorship W2788014765A5080828884 @default.
- W2788014765 hasConcept C115961682 @default.
- W2788014765 hasConcept C119857082 @default.
- W2788014765 hasConcept C134306372 @default.
- W2788014765 hasConcept C150899416 @default.
- W2788014765 hasConcept C153180895 @default.
- W2788014765 hasConcept C154945302 @default.
- W2788014765 hasConcept C177454536 @default.
- W2788014765 hasConcept C2776321320 @default.
- W2788014765 hasConcept C2779803651 @default.
- W2788014765 hasConcept C2781238097 @default.
- W2788014765 hasConcept C2988773926 @default.
- W2788014765 hasConcept C33923547 @default.
- W2788014765 hasConcept C36503486 @default.
- W2788014765 hasConcept C37736160 @default.
- W2788014765 hasConcept C39890363 @default.
- W2788014765 hasConcept C41008148 @default.
- W2788014765 hasConcept C76155785 @default.
- W2788014765 hasConcept C94915269 @default.
- W2788014765 hasConceptScore W2788014765C115961682 @default.
- W2788014765 hasConceptScore W2788014765C119857082 @default.
- W2788014765 hasConceptScore W2788014765C134306372 @default.
- W2788014765 hasConceptScore W2788014765C150899416 @default.
- W2788014765 hasConceptScore W2788014765C153180895 @default.
- W2788014765 hasConceptScore W2788014765C154945302 @default.
- W2788014765 hasConceptScore W2788014765C177454536 @default.
- W2788014765 hasConceptScore W2788014765C2776321320 @default.
- W2788014765 hasConceptScore W2788014765C2779803651 @default.
- W2788014765 hasConceptScore W2788014765C2781238097 @default.
- W2788014765 hasConceptScore W2788014765C2988773926 @default.
- W2788014765 hasConceptScore W2788014765C33923547 @default.
- W2788014765 hasConceptScore W2788014765C36503486 @default.
- W2788014765 hasConceptScore W2788014765C37736160 @default.
- W2788014765 hasConceptScore W2788014765C39890363 @default.
- W2788014765 hasConceptScore W2788014765C41008148 @default.
- W2788014765 hasConceptScore W2788014765C76155785 @default.
- W2788014765 hasConceptScore W2788014765C94915269 @default.
- W2788014765 hasLocation W27880147651 @default.
- W2788014765 hasOpenAccess W2788014765 @default.
- W2788014765 hasPrimaryLocation W27880147651 @default.
- W2788014765 hasRelatedWork W2099471712 @default.
- W2788014765 hasRelatedWork W2579352881 @default.
- W2788014765 hasRelatedWork W2802315171 @default.
- W2788014765 hasRelatedWork W2805277890 @default.
- W2788014765 hasRelatedWork W2850232725 @default.
- W2788014765 hasRelatedWork W2927384416 @default.
- W2788014765 hasRelatedWork W2952499146 @default.
- W2788014765 hasRelatedWork W2963675401 @default.
- W2788014765 hasRelatedWork W2981335848 @default.
- W2788014765 hasRelatedWork W2984809863 @default.
- W2788014765 hasRelatedWork W2997019934 @default.
- W2788014765 hasRelatedWork W3033022871 @default.
- W2788014765 hasRelatedWork W3044881747 @default.
- W2788014765 hasRelatedWork W3084170234 @default.
- W2788014765 hasRelatedWork W3089357337 @default.
- W2788014765 hasRelatedWork W3096458759 @default.
- W2788014765 hasRelatedWork W3131018743 @default.
- W2788014765 hasRelatedWork W3156354504 @default.
- W2788014765 hasRelatedWork W3194214700 @default.
- W2788014765 hasRelatedWork W3204731714 @default.
- W2788014765 isParatext "false" @default.
- W2788014765 isRetracted "false" @default.
- W2788014765 magId "2788014765" @default.
- W2788014765 workType "article" @default.