Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308237189> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4308237189 abstract "In the last few years, we have witnessed the rise of a series of deep learning methods to generate synthetic images that look extremely realistic. These techniques prove useful in the movie industry and for artistic purposes. However, they also prove dangerous if used to spread fake news or to generate fake online accounts. For this reason, detecting if an image is an actual photograph or has been synthetically generated is becoming an urgent necessity. This paper proposes a detector of synthetic images based on an ensemble of Convolutional Neural Networks (CNNs). We consider the problem of detecting images generated with techniques not available at training time. This is a common scenario, given that new image generators are published more and more frequently. To solve this issue, we leverage two main ideas: (i) CNNs should provide orthogonal results to better contribute to the ensemble; (ii) the original-image class is better defined than the synthetic-image one, thus it should be better trusted at testing time. Experiments show that pursuing these two ideas improves the detector accuracy on NVIDIA's newly generated StyleGAN3 images, never used in training." @default.
- W4308237189 created "2022-11-09" @default.
- W4308237189 creator A5005378965 @default.
- W4308237189 creator A5043644234 @default.
- W4308237189 creator A5046125100 @default.
- W4308237189 creator A5051370303 @default.
- W4308237189 date "2022-10-16" @default.
- W4308237189 modified "2023-10-14" @default.
- W4308237189 title "Detecting Gan-Generated Images by Orthogonal Training of Multiple CNNs" @default.
- W4308237189 cites W2907295878 @default.
- W4308237189 cites W3034577585 @default.
- W4308237189 cites W3099319035 @default.
- W4308237189 cites W3133516147 @default.
- W4308237189 cites W3133672610 @default.
- W4308237189 cites W3158766194 @default.
- W4308237189 cites W3173126908 @default.
- W4308237189 cites W3180355996 @default.
- W4308237189 cites W3180770160 @default.
- W4308237189 cites W4200560037 @default.
- W4308237189 cites W4206030296 @default.
- W4308237189 cites W4213187648 @default.
- W4308237189 cites W4285176942 @default.
- W4308237189 doi "https://doi.org/10.1109/icip46576.2022.9897310" @default.
- W4308237189 hasPublicationYear "2022" @default.
- W4308237189 type Work @default.
- W4308237189 citedByCount "4" @default.
- W4308237189 countsByYear W43082371892023 @default.
- W4308237189 crossrefType "proceedings-article" @default.
- W4308237189 hasAuthorship W4308237189A5005378965 @default.
- W4308237189 hasAuthorship W4308237189A5043644234 @default.
- W4308237189 hasAuthorship W4308237189A5046125100 @default.
- W4308237189 hasAuthorship W4308237189A5051370303 @default.
- W4308237189 hasBestOaLocation W43082371892 @default.
- W4308237189 hasConcept C108583219 @default.
- W4308237189 hasConcept C115961682 @default.
- W4308237189 hasConcept C119857082 @default.
- W4308237189 hasConcept C153083717 @default.
- W4308237189 hasConcept C153180895 @default.
- W4308237189 hasConcept C154945302 @default.
- W4308237189 hasConcept C31972630 @default.
- W4308237189 hasConcept C41008148 @default.
- W4308237189 hasConcept C51632099 @default.
- W4308237189 hasConcept C76155785 @default.
- W4308237189 hasConcept C81363708 @default.
- W4308237189 hasConcept C94915269 @default.
- W4308237189 hasConceptScore W4308237189C108583219 @default.
- W4308237189 hasConceptScore W4308237189C115961682 @default.
- W4308237189 hasConceptScore W4308237189C119857082 @default.
- W4308237189 hasConceptScore W4308237189C153083717 @default.
- W4308237189 hasConceptScore W4308237189C153180895 @default.
- W4308237189 hasConceptScore W4308237189C154945302 @default.
- W4308237189 hasConceptScore W4308237189C31972630 @default.
- W4308237189 hasConceptScore W4308237189C41008148 @default.
- W4308237189 hasConceptScore W4308237189C51632099 @default.
- W4308237189 hasConceptScore W4308237189C76155785 @default.
- W4308237189 hasConceptScore W4308237189C81363708 @default.
- W4308237189 hasConceptScore W4308237189C94915269 @default.
- W4308237189 hasFunder F4320338294 @default.
- W4308237189 hasLocation W43082371891 @default.
- W4308237189 hasLocation W43082371892 @default.
- W4308237189 hasOpenAccess W4308237189 @default.
- W4308237189 hasPrimaryLocation W43082371891 @default.
- W4308237189 hasRelatedWork W2731899572 @default.
- W4308237189 hasRelatedWork W2795865589 @default.
- W4308237189 hasRelatedWork W2999805992 @default.
- W4308237189 hasRelatedWork W3116150086 @default.
- W4308237189 hasRelatedWork W3133861977 @default.
- W4308237189 hasRelatedWork W4200173597 @default.
- W4308237189 hasRelatedWork W4291897433 @default.
- W4308237189 hasRelatedWork W4312417841 @default.
- W4308237189 hasRelatedWork W4321369474 @default.
- W4308237189 hasRelatedWork W4380075502 @default.
- W4308237189 isParatext "false" @default.
- W4308237189 isRetracted "false" @default.
- W4308237189 workType "article" @default.