FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200176170> ?p ?o ?g. }

• W4200176170 endingPage "e760" @default.
• W4200176170 startingPage "e760" @default.
• W4200176170 abstract "Image data collection and labelling is costly or difficult in many real applications. Generating diverse and controllable images using conditional generative adversarial networks (GANs) for data augmentation from a small dataset is promising but challenging as deep convolutional neural networks need a large training dataset to achieve reasonable performance in general. However, unlabeled and incomplete features (e.g., unintegral edges, simplified lines, hand-drawn sketches, discontinuous geometry shapes, etc.) can be conveniently obtained through pre-processing the training images and can be used for image data augmentation. This paper proposes a conditional GAN framework for facial image augmentation using a very small training dataset and incomplete or modified edge features as conditional input for diversity. The proposed method defines a new domain or space for refining interim images to prevent overfitting caused by using a very small training dataset and enhance the tolerance of distortions caused by incomplete edge features, which effectively improves the quality of facial image augmentation with diversity. Experimental results have shown that the proposed method can generate high-quality images of good diversity when the GANs are trained using very sparse edges and a small number of training samples. Compared to the state-of-the-art edge-to-image translation methods that directly convert sparse edges to images, when using a small training dataset, the proposed conditional GAN framework can generate facial images with desirable diversity and acceptable distortions for dataset augmentation and significantly outperform the existing methods in terms of the quality of synthesised images, evaluated by Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) scores." @default.
• W4200176170 created "2021-12-31" @default.
• W4200176170 creator A5041507817 @default.
• W4200176170 creator A5082525691 @default.
• W4200176170 date "2021-11-17" @default.
• W4200176170 modified "2023-09-24" @default.
• W4200176170 title "Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input" @default.
• W4200176170 cites W1775475380 @default.
• W4200176170 cites W1834627138 @default.
• W4200176170 cites W1901129140 @default.
• W4200176170 cites W2026019603 @default.
• W4200176170 cites W2119381621 @default.
• W4200176170 cites W2145023731 @default.
• W4200176170 cites W2298992465 @default.
• W4200176170 cites W2475287302 @default.
• W4200176170 cites W2738588019 @default.
• W4200176170 cites W2809598685 @default.
• W4200176170 cites W2905562891 @default.
• W4200176170 cites W2928133111 @default.
• W4200176170 cites W2952056941 @default.
• W4200176170 cites W2954996726 @default.
• W4200176170 cites W2962793481 @default.
• W4200176170 cites W2963073614 @default.
• W4200176170 cites W2963184176 @default.
• W4200176170 cites W2963444790 @default.
• W4200176170 cites W2963561004 @default.
• W4200176170 cites W2963649420 @default.
• W4200176170 cites W2963800363 @default.
• W4200176170 cites W2964287360 @default.
• W4200176170 cites W2964833232 @default.
• W4200176170 cites W2982763192 @default.
• W4200176170 cites W2989505547 @default.
• W4200176170 cites W3013409203 @default.
• W4200176170 cites W3018252856 @default.
• W4200176170 cites W3028262853 @default.
• W4200176170 cites W3094169176 @default.
• W4200176170 cites W3101819852 @default.
• W4200176170 cites W3194473846 @default.
• W4200176170 cites W4256052613 @default.
• W4200176170 cites W4288079578 @default.
• W4200176170 doi "https://doi.org/10.7717/peerj-cs.760" @default.
• W4200176170 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34901424" @default.
• W4200176170 hasPublicationYear "2021" @default.
• W4200176170 type Work @default.
• W4200176170 citedByCount "1" @default.
• W4200176170 countsByYear W42001761702023 @default.
• W4200176170 crossrefType "journal-article" @default.
• W4200176170 hasAuthorship W4200176170A5041507817 @default.
• W4200176170 hasAuthorship W4200176170A5082525691 @default.
• W4200176170 hasBestOaLocation W42001761701 @default.
• W4200176170 hasConcept C115961682 @default.
• W4200176170 hasConcept C138885662 @default.
• W4200176170 hasConcept C153180895 @default.
• W4200176170 hasConcept C154945302 @default.
• W4200176170 hasConcept C162307627 @default.
• W4200176170 hasConcept C22019652 @default.
• W4200176170 hasConcept C2776401178 @default.
• W4200176170 hasConcept C31972630 @default.
• W4200176170 hasConcept C41008148 @default.
• W4200176170 hasConcept C41895202 @default.
• W4200176170 hasConcept C50644808 @default.
• W4200176170 hasConcept C81363708 @default.
• W4200176170 hasConceptScore W4200176170C115961682 @default.
• W4200176170 hasConceptScore W4200176170C138885662 @default.
• W4200176170 hasConceptScore W4200176170C153180895 @default.
• W4200176170 hasConceptScore W4200176170C154945302 @default.
• W4200176170 hasConceptScore W4200176170C162307627 @default.
• W4200176170 hasConceptScore W4200176170C22019652 @default.
• W4200176170 hasConceptScore W4200176170C2776401178 @default.
• W4200176170 hasConceptScore W4200176170C31972630 @default.
• W4200176170 hasConceptScore W4200176170C41008148 @default.
• W4200176170 hasConceptScore W4200176170C41895202 @default.
• W4200176170 hasConceptScore W4200176170C50644808 @default.
• W4200176170 hasConceptScore W4200176170C81363708 @default.
• W4200176170 hasLocation W42001761701 @default.
• W4200176170 hasLocation W42001761702 @default.
• W4200176170 hasLocation W42001761703 @default.
• W4200176170 hasLocation W42001761704 @default.
• W4200176170 hasLocation W42001761705 @default.
• W4200176170 hasLocation W42001761706 @default.
• W4200176170 hasOpenAccess W4200176170 @default.
• W4200176170 hasPrimaryLocation W42001761701 @default.
• W4200176170 hasRelatedWork W1504288058 @default.
• W4200176170 hasRelatedWork W2167293474 @default.
• W4200176170 hasRelatedWork W2331674254 @default.
• W4200176170 hasRelatedWork W2767651786 @default.
• W4200176170 hasRelatedWork W3012393889 @default.
• W4200176170 hasRelatedWork W3042897387 @default.
• W4200176170 hasRelatedWork W3081496756 @default.
• W4200176170 hasRelatedWork W3127819136 @default.
• W4200176170 hasRelatedWork W4220996320 @default.
• W4200176170 hasRelatedWork W785854688 @default.
• W4200176170 hasVolume "7" @default.
• W4200176170 isParatext "false" @default.
• W4200176170 isRetracted "false" @default.
• W4200176170 workType "article" @default.