Matches in SemOpenAlex for { <https://semopenalex.org/work/W2593493485> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2593493485 abstract "We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms which are more flexible than existing codecs. Autoencoders have the potential to address this need, but are difficult to optimize directly due to the inherent non-differentiabilty of the compression loss. We here show that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs. Our network is furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images. This is in contrast to previous work on autoencoders for compression using coarser approximations, shallower architectures, computationally expensive methods, or focusing on small images." @default.
- W2593493485 created "2017-03-16" @default.
- W2593493485 creator A5018244514 @default.
- W2593493485 creator A5028376903 @default.
- W2593493485 creator A5041064065 @default.
- W2593493485 creator A5052054395 @default.
- W2593493485 date "2017-03-01" @default.
- W2593493485 modified "2023-09-25" @default.
- W2593493485 title "Lossy Image Compression with Compressive Autoencoders" @default.
- W2593493485 doi "https://doi.org/10.17863/cam.51995" @default.
- W2593493485 hasPublicationYear "2017" @default.
- W2593493485 type Work @default.
- W2593493485 sameAs 2593493485 @default.
- W2593493485 citedByCount "114" @default.
- W2593493485 countsByYear W25934934852017 @default.
- W2593493485 countsByYear W25934934852018 @default.
- W2593493485 countsByYear W25934934852019 @default.
- W2593493485 countsByYear W25934934852020 @default.
- W2593493485 countsByYear W25934934852021 @default.
- W2593493485 crossrefType "proceedings-article" @default.
- W2593493485 hasAuthorship W2593493485A5018244514 @default.
- W2593493485 hasAuthorship W2593493485A5028376903 @default.
- W2593493485 hasAuthorship W2593493485A5041064065 @default.
- W2593493485 hasAuthorship W2593493485A5052054395 @default.
- W2593493485 hasConcept C113775141 @default.
- W2593493485 hasConcept C115961682 @default.
- W2593493485 hasConcept C13481523 @default.
- W2593493485 hasConcept C154945302 @default.
- W2593493485 hasConcept C159985019 @default.
- W2593493485 hasConcept C161765866 @default.
- W2593493485 hasConcept C165021410 @default.
- W2593493485 hasConcept C180016635 @default.
- W2593493485 hasConcept C192562407 @default.
- W2593493485 hasConcept C198751489 @default.
- W2593493485 hasConcept C41008148 @default.
- W2593493485 hasConcept C69216139 @default.
- W2593493485 hasConcept C78548338 @default.
- W2593493485 hasConcept C81081738 @default.
- W2593493485 hasConcept C9390403 @default.
- W2593493485 hasConcept C9417928 @default.
- W2593493485 hasConceptScore W2593493485C113775141 @default.
- W2593493485 hasConceptScore W2593493485C115961682 @default.
- W2593493485 hasConceptScore W2593493485C13481523 @default.
- W2593493485 hasConceptScore W2593493485C154945302 @default.
- W2593493485 hasConceptScore W2593493485C159985019 @default.
- W2593493485 hasConceptScore W2593493485C161765866 @default.
- W2593493485 hasConceptScore W2593493485C165021410 @default.
- W2593493485 hasConceptScore W2593493485C180016635 @default.
- W2593493485 hasConceptScore W2593493485C192562407 @default.
- W2593493485 hasConceptScore W2593493485C198751489 @default.
- W2593493485 hasConceptScore W2593493485C41008148 @default.
- W2593493485 hasConceptScore W2593493485C69216139 @default.
- W2593493485 hasConceptScore W2593493485C78548338 @default.
- W2593493485 hasConceptScore W2593493485C81081738 @default.
- W2593493485 hasConceptScore W2593493485C9390403 @default.
- W2593493485 hasConceptScore W2593493485C9417928 @default.
- W2593493485 hasLocation W25934934851 @default.
- W2593493485 hasOpenAccess W2593493485 @default.
- W2593493485 hasPrimaryLocation W25934934851 @default.
- W2593493485 hasRelatedWork W1580389772 @default.
- W2593493485 hasRelatedWork W1959608418 @default.
- W2593493485 hasRelatedWork W2099471712 @default.
- W2593493485 hasRelatedWork W2133665775 @default.
- W2593493485 hasRelatedWork W2140196014 @default.
- W2593493485 hasRelatedWork W2146395539 @default.
- W2593493485 hasRelatedWork W2194775991 @default.
- W2593493485 hasRelatedWork W2597747080 @default.
- W2593493485 hasRelatedWork W2604392022 @default.
- W2593493485 hasRelatedWork W2892278106 @default.
- W2593493485 hasRelatedWork W2893920456 @default.
- W2593493485 hasRelatedWork W2962676454 @default.
- W2593493485 hasRelatedWork W2962790638 @default.
- W2593493485 hasRelatedWork W2962891349 @default.
- W2593493485 hasRelatedWork W2963149687 @default.
- W2593493485 hasRelatedWork W2963449488 @default.
- W2593493485 hasRelatedWork W2964098744 @default.
- W2593493485 hasRelatedWork W2964121744 @default.
- W2593493485 hasRelatedWork W2964164354 @default.
- W2593493485 hasRelatedWork W2981613960 @default.
- W2593493485 isParatext "false" @default.
- W2593493485 isRetracted "false" @default.
- W2593493485 magId "2593493485" @default.
- W2593493485 workType "article" @default.