Matches in SemOpenAlex for { <https://semopenalex.org/work/W3178160553> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3178160553 endingPage "107284" @default.
- W3178160553 startingPage "107284" @default.
- W3178160553 abstract "Existing learned-based image compression methods have shown impressive performance. However, they rely mostly on the consistent distribution between training and test images, which reduces the robustness of the training model. In this paper, we propose a novel compression method called sparse flow adversarial model (SFAM). SFAM employs a deep generative framework to learn a reversible and stable mapping between image distributions, thus it can work in varied scenes for robust compression. The mapping explores the sparsity of the image by combining linear and nonlinear transformations, rather than extracting the features of a particular dataset as is the case with other learning-based methods. Moreover, a sparse adversarial map is introduced into SFAM, to constrain the SFAM to generate sparser features for efficient compression. Extensive experiments are performed on different datasets, in which the effectiveness and robustness of the proposed method are verified. Meanwhile, SFAM is trained only once and it can work well on three different datasets, which also prove the robustness of the proposed SFAM." @default.
- W3178160553 created "2021-07-19" @default.
- W3178160553 creator A5007544409 @default.
- W3178160553 creator A5053487344 @default.
- W3178160553 creator A5056367449 @default.
- W3178160553 creator A5067739631 @default.
- W3178160553 creator A5080902896 @default.
- W3178160553 date "2021-10-01" @default.
- W3178160553 modified "2023-09-27" @default.
- W3178160553 title "Sparse flow adversarial model for robust image compression" @default.
- W3178160553 cites W2040903332 @default.
- W3178160553 cites W2090374302 @default.
- W3178160553 cites W2108598243 @default.
- W3178160553 cites W2114770744 @default.
- W3178160553 cites W2153638435 @default.
- W3178160553 cites W2171033838 @default.
- W3178160553 cites W2593414223 @default.
- W3178160553 cites W2740336064 @default.
- W3178160553 cites W2798309714 @default.
- W3178160553 cites W2895476614 @default.
- W3178160553 cites W2921404719 @default.
- W3178160553 cites W2962749812 @default.
- W3178160553 cites W2963149687 @default.
- W3178160553 cites W2970340508 @default.
- W3178160553 cites W3003225782 @default.
- W3178160553 cites W3007832592 @default.
- W3178160553 cites W3011270868 @default.
- W3178160553 cites W3012669251 @default.
- W3178160553 cites W3039121139 @default.
- W3178160553 cites W3044326844 @default.
- W3178160553 cites W3088389255 @default.
- W3178160553 doi "https://doi.org/10.1016/j.knosys.2021.107284" @default.
- W3178160553 hasPublicationYear "2021" @default.
- W3178160553 type Work @default.
- W3178160553 sameAs 3178160553 @default.
- W3178160553 citedByCount "1" @default.
- W3178160553 countsByYear W31781605532022 @default.
- W3178160553 crossrefType "journal-article" @default.
- W3178160553 hasAuthorship W3178160553A5007544409 @default.
- W3178160553 hasAuthorship W3178160553A5053487344 @default.
- W3178160553 hasAuthorship W3178160553A5056367449 @default.
- W3178160553 hasAuthorship W3178160553A5067739631 @default.
- W3178160553 hasAuthorship W3178160553A5080902896 @default.
- W3178160553 hasConcept C104317684 @default.
- W3178160553 hasConcept C115961682 @default.
- W3178160553 hasConcept C121332964 @default.
- W3178160553 hasConcept C13481523 @default.
- W3178160553 hasConcept C153180895 @default.
- W3178160553 hasConcept C154945302 @default.
- W3178160553 hasConcept C158622935 @default.
- W3178160553 hasConcept C159985019 @default.
- W3178160553 hasConcept C180016635 @default.
- W3178160553 hasConcept C185592680 @default.
- W3178160553 hasConcept C192562407 @default.
- W3178160553 hasConcept C37736160 @default.
- W3178160553 hasConcept C39890363 @default.
- W3178160553 hasConcept C41008148 @default.
- W3178160553 hasConcept C55493867 @default.
- W3178160553 hasConcept C62520636 @default.
- W3178160553 hasConcept C63479239 @default.
- W3178160553 hasConcept C9417928 @default.
- W3178160553 hasConceptScore W3178160553C104317684 @default.
- W3178160553 hasConceptScore W3178160553C115961682 @default.
- W3178160553 hasConceptScore W3178160553C121332964 @default.
- W3178160553 hasConceptScore W3178160553C13481523 @default.
- W3178160553 hasConceptScore W3178160553C153180895 @default.
- W3178160553 hasConceptScore W3178160553C154945302 @default.
- W3178160553 hasConceptScore W3178160553C158622935 @default.
- W3178160553 hasConceptScore W3178160553C159985019 @default.
- W3178160553 hasConceptScore W3178160553C180016635 @default.
- W3178160553 hasConceptScore W3178160553C185592680 @default.
- W3178160553 hasConceptScore W3178160553C192562407 @default.
- W3178160553 hasConceptScore W3178160553C37736160 @default.
- W3178160553 hasConceptScore W3178160553C39890363 @default.
- W3178160553 hasConceptScore W3178160553C41008148 @default.
- W3178160553 hasConceptScore W3178160553C55493867 @default.
- W3178160553 hasConceptScore W3178160553C62520636 @default.
- W3178160553 hasConceptScore W3178160553C63479239 @default.
- W3178160553 hasConceptScore W3178160553C9417928 @default.
- W3178160553 hasLocation W31781605531 @default.
- W3178160553 hasOpenAccess W3178160553 @default.
- W3178160553 hasPrimaryLocation W31781605531 @default.
- W3178160553 hasRelatedWork W2850820022 @default.
- W3178160553 hasRelatedWork W2901368259 @default.
- W3178160553 hasRelatedWork W2903311573 @default.
- W3178160553 hasRelatedWork W2973444776 @default.
- W3178160553 hasRelatedWork W3024390022 @default.
- W3178160553 hasRelatedWork W3156291593 @default.
- W3178160553 hasRelatedWork W3198184493 @default.
- W3178160553 hasRelatedWork W4313479464 @default.
- W3178160553 hasRelatedWork W4322759769 @default.
- W3178160553 hasRelatedWork W4367722749 @default.
- W3178160553 hasVolume "229" @default.
- W3178160553 isParatext "false" @default.
- W3178160553 isRetracted "false" @default.
- W3178160553 magId "3178160553" @default.
- W3178160553 workType "article" @default.