Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204105723> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3204105723 abstract "Learned image compression is making good progress in recent years. Peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM) are the two most popular evaluation metrics. As different metrics only reflect certain aspects of human perception, works in this field normally optimize two models using PSNR and MS-SSIM as loss function separately, which is suboptimal and makes it difficult to select the model with best visual quality or overall performance. Towards solving this problem, we propose to Harmonize optimization metrics in Learned Image Compression (HLIC) using online loss function adaptation by reinforcement learning. By doing so, we are able to leverage the advantages of both PSNR and MS-SSIM, achieving better visual quality and higher VMAF score. To our knowledge, our work is the first to explore automatic loss function adaptation for harmonizing optimization metrics in low level vision tasks like learned image compression." @default.
- W3204105723 created "2021-10-11" @default.
- W3204105723 creator A5003642180 @default.
- W3204105723 creator A5047234623 @default.
- W3204105723 creator A5056146772 @default.
- W3204105723 creator A5056572647 @default.
- W3204105723 creator A5062642187 @default.
- W3204105723 creator A5064363699 @default.
- W3204105723 date "2021-09-30" @default.
- W3204105723 modified "2023-10-17" @default.
- W3204105723 title "HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning" @default.
- W3204105723 cites W1580389772 @default.
- W3204105723 cites W1915485278 @default.
- W3204105723 cites W2046119925 @default.
- W3204105723 cites W2108598243 @default.
- W3204105723 cites W2117804578 @default.
- W3204105723 cites W2118217749 @default.
- W3204105723 cites W2119717200 @default.
- W3204105723 cites W2129768577 @default.
- W3204105723 cites W2331128040 @default.
- W3204105723 cites W2597747080 @default.
- W3204105723 cites W2736601468 @default.
- W3204105723 cites W2891212213 @default.
- W3204105723 cites W2892278106 @default.
- W3204105723 cites W2962676454 @default.
- W3204105723 cites W2962891349 @default.
- W3204105723 cites W2963149687 @default.
- W3204105723 cites W2963184621 @default.
- W3204105723 cites W2963449488 @default.
- W3204105723 cites W2963636093 @default.
- W3204105723 cites W2964098744 @default.
- W3204105723 cites W2982853315 @default.
- W3204105723 cites W2985793077 @default.
- W3204105723 cites W3034293449 @default.
- W3204105723 cites W3034469748 @default.
- W3204105723 cites W3035335920 @default.
- W3204105723 cites W3092899229 @default.
- W3204105723 cites W3095497211 @default.
- W3204105723 cites W3100456687 @default.
- W3204105723 cites W3103781353 @default.
- W3204105723 cites W3126658316 @default.
- W3204105723 cites W3175541956 @default.
- W3204105723 doi "https://doi.org/10.48550/arxiv.2109.14863" @default.
- W3204105723 hasPublicationYear "2021" @default.
- W3204105723 type Work @default.
- W3204105723 sameAs 3204105723 @default.
- W3204105723 citedByCount "0" @default.
- W3204105723 crossrefType "posted-content" @default.
- W3204105723 hasAuthorship W3204105723A5003642180 @default.
- W3204105723 hasAuthorship W3204105723A5047234623 @default.
- W3204105723 hasAuthorship W3204105723A5056146772 @default.
- W3204105723 hasAuthorship W3204105723A5056572647 @default.
- W3204105723 hasAuthorship W3204105723A5062642187 @default.
- W3204105723 hasAuthorship W3204105723A5064363699 @default.
- W3204105723 hasBestOaLocation W32041057231 @default.
- W3204105723 hasConcept C115961682 @default.
- W3204105723 hasConcept C119857082 @default.
- W3204105723 hasConcept C120665830 @default.
- W3204105723 hasConcept C121332964 @default.
- W3204105723 hasConcept C13481523 @default.
- W3204105723 hasConcept C139807058 @default.
- W3204105723 hasConcept C153083717 @default.
- W3204105723 hasConcept C153180895 @default.
- W3204105723 hasConcept C154945302 @default.
- W3204105723 hasConcept C160086991 @default.
- W3204105723 hasConcept C41008148 @default.
- W3204105723 hasConcept C55020928 @default.
- W3204105723 hasConcept C9417928 @default.
- W3204105723 hasConcept C97541855 @default.
- W3204105723 hasConceptScore W3204105723C115961682 @default.
- W3204105723 hasConceptScore W3204105723C119857082 @default.
- W3204105723 hasConceptScore W3204105723C120665830 @default.
- W3204105723 hasConceptScore W3204105723C121332964 @default.
- W3204105723 hasConceptScore W3204105723C13481523 @default.
- W3204105723 hasConceptScore W3204105723C139807058 @default.
- W3204105723 hasConceptScore W3204105723C153083717 @default.
- W3204105723 hasConceptScore W3204105723C153180895 @default.
- W3204105723 hasConceptScore W3204105723C154945302 @default.
- W3204105723 hasConceptScore W3204105723C160086991 @default.
- W3204105723 hasConceptScore W3204105723C41008148 @default.
- W3204105723 hasConceptScore W3204105723C55020928 @default.
- W3204105723 hasConceptScore W3204105723C9417928 @default.
- W3204105723 hasConceptScore W3204105723C97541855 @default.
- W3204105723 hasLocation W32041057231 @default.
- W3204105723 hasOpenAccess W3204105723 @default.
- W3204105723 hasPrimaryLocation W32041057231 @default.
- W3204105723 hasRelatedWork W1619057518 @default.
- W3204105723 hasRelatedWork W1677446238 @default.
- W3204105723 hasRelatedWork W2235797036 @default.
- W3204105723 hasRelatedWork W2572271943 @default.
- W3204105723 hasRelatedWork W3022038857 @default.
- W3204105723 hasRelatedWork W3170628611 @default.
- W3204105723 hasRelatedWork W3203000071 @default.
- W3204105723 hasRelatedWork W4307308173 @default.
- W3204105723 hasRelatedWork W4318719223 @default.
- W3204105723 hasRelatedWork W4319083788 @default.
- W3204105723 isParatext "false" @default.
- W3204105723 isRetracted "false" @default.
- W3204105723 magId "3204105723" @default.
- W3204105723 workType "article" @default.