Matches in SemOpenAlex for { <https://semopenalex.org/work/W2911455861> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2911455861 abstract "In this paper, we present a generative adversarial network framework that generates compressed images instead of synthesizing raw RGB images and compressing them separately. In the real world, most images and videos are stored and transferred in a compressed format to save storage capacity and data transfer bandwidth. However, since typical generative adversarial networks generate raw RGB images, those generated images need to be compressed by a post-processing stage to reduce the data size. Among image compression methods, JPEG has been one of the most commonly used lossy compression methods for still images. Hence, we propose a novel framework that generates JPEG compressed images using generative adversarial networks. The novel generator consists of the proposed locally connected layers, chroma subsampling layers, quantization layers, residual blocks, and convolution layers. The locally connected layer is proposed to enable block-based operations. We also discuss training strategies for the proposed architecture including the loss function and the transformation between its generator and its discriminator. The proposed method is evaluated using the publicly available CIFAR-10 dataset and LSUN bedroom dataset. The results demonstrate that the proposed method is able to generate compressed data with competitive qualities. The proposed method is a promising baseline method for joint image generation and compression using generative adversarial networks." @default.
- W2911455861 created "2019-02-21" @default.
- W2911455861 creator A5002282875 @default.
- W2911455861 creator A5032328702 @default.
- W2911455861 creator A5061248117 @default.
- W2911455861 date "2019-01-23" @default.
- W2911455861 modified "2023-09-24" @default.
- W2911455861 title "Toward Joint Image Generation and Compression using Generative Adversarial Networks." @default.
- W2911455861 cites W1492380776 @default.
- W2911455861 cites W2005245503 @default.
- W2911455861 cites W2031614119 @default.
- W2911455861 cites W2060108852 @default.
- W2911455861 cites W2078179989 @default.
- W2911455861 cites W2096542306 @default.
- W2911455861 cites W2099471712 @default.
- W2911455861 cites W2129241738 @default.
- W2911455861 cites W2140196014 @default.
- W2911455861 cites W2150013946 @default.
- W2911455861 cites W2173520492 @default.
- W2911455861 cites W2183341477 @default.
- W2911455861 cites W2520707650 @default.
- W2911455861 cites W2612336981 @default.
- W2911455861 cites W2739748921 @default.
- W2911455861 cites W2746654391 @default.
- W2911455861 cites W2891810238 @default.
- W2911455861 cites W2950237263 @default.
- W2911455861 cites W2962790638 @default.
- W2911455861 cites W2962879692 @default.
- W2911455861 cites W2963149687 @default.
- W2911455861 cites W2963352069 @default.
- W2911455861 cites W2963373786 @default.
- W2911455861 cites W2963800363 @default.
- W2911455861 cites W2963841322 @default.
- W2911455861 cites W2963942586 @default.
- W2911455861 cites W2963981733 @default.
- W2911455861 cites W2964318715 @default.
- W2911455861 cites W3118608800 @default.
- W2911455861 cites W967544008 @default.
- W2911455861 hasPublicationYear "2019" @default.
- W2911455861 type Work @default.
- W2911455861 sameAs 2911455861 @default.
- W2911455861 citedByCount "0" @default.
- W2911455861 crossrefType "posted-content" @default.
- W2911455861 hasAuthorship W2911455861A5002282875 @default.
- W2911455861 hasAuthorship W2911455861A5032328702 @default.
- W2911455861 hasAuthorship W2911455861A5061248117 @default.
- W2911455861 hasConcept C115961682 @default.
- W2911455861 hasConcept C13481523 @default.
- W2911455861 hasConcept C153180895 @default.
- W2911455861 hasConcept C154945302 @default.
- W2911455861 hasConcept C165021410 @default.
- W2911455861 hasConcept C198751489 @default.
- W2911455861 hasConcept C31972630 @default.
- W2911455861 hasConcept C41008148 @default.
- W2911455861 hasConcept C78548338 @default.
- W2911455861 hasConcept C9417928 @default.
- W2911455861 hasConceptScore W2911455861C115961682 @default.
- W2911455861 hasConceptScore W2911455861C13481523 @default.
- W2911455861 hasConceptScore W2911455861C153180895 @default.
- W2911455861 hasConceptScore W2911455861C154945302 @default.
- W2911455861 hasConceptScore W2911455861C165021410 @default.
- W2911455861 hasConceptScore W2911455861C198751489 @default.
- W2911455861 hasConceptScore W2911455861C31972630 @default.
- W2911455861 hasConceptScore W2911455861C41008148 @default.
- W2911455861 hasConceptScore W2911455861C78548338 @default.
- W2911455861 hasConceptScore W2911455861C9417928 @default.
- W2911455861 hasOpenAccess W2911455861 @default.
- W2911455861 hasRelatedWork W1577694829 @default.
- W2911455861 hasRelatedWork W2182257114 @default.
- W2911455861 hasRelatedWork W2404306640 @default.
- W2911455861 hasRelatedWork W2773245934 @default.
- W2911455861 hasRelatedWork W2785633065 @default.
- W2911455861 hasRelatedWork W2786977213 @default.
- W2911455861 hasRelatedWork W2792008807 @default.
- W2911455861 hasRelatedWork W2912933380 @default.
- W2911455861 hasRelatedWork W2989997937 @default.
- W2911455861 hasRelatedWork W3008546195 @default.
- W2911455861 hasRelatedWork W3090905439 @default.
- W2911455861 hasRelatedWork W3102075482 @default.
- W2911455861 hasRelatedWork W3127190345 @default.
- W2911455861 hasRelatedWork W3129840523 @default.
- W2911455861 hasRelatedWork W3143350771 @default.
- W2911455861 hasRelatedWork W3163122488 @default.
- W2911455861 hasRelatedWork W3176512213 @default.
- W2911455861 hasRelatedWork W3195126222 @default.
- W2911455861 hasRelatedWork W2739962289 @default.
- W2911455861 hasRelatedWork W2962306623 @default.
- W2911455861 isParatext "false" @default.
- W2911455861 isRetracted "false" @default.
- W2911455861 magId "2911455861" @default.
- W2911455861 workType "article" @default.