Matches in SemOpenAlex for { <https://semopenalex.org/work/W2993074870> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2993074870 abstract "Face Super-Resolution is a subset of Super Resolution (SR) that aims to retrieve a high-resolution (HR) image of a face from a lower resolution input. Recently, Deep Learning (DL) methods have improved drastically the quality of SR generated images. However, these qualitative improvements are not always followed by quantitative improvements in the traditional metrics of the area, namely PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index). In some cases, models that perform better in opinion scores and qualitative evaluation have worse performance in these metrics, indicating they are not sufficiently informative. To address this issue we propose a task-based evaluation procedure based on the comparative performance of face recognition algorithms on HR and SR images to evaluate how well the models retrieve high-frequency and identity defining information. Furthermore, as our face recognition model is differentiable, this leads to a novel loss function that can be optimized to improve performance in these tasks. We successfully apply our evaluation method to validate this training method, yielding promising results." @default.
- W2993074870 created "2019-12-13" @default.
- W2993074870 creator A5006191190 @default.
- W2993074870 creator A5045928378 @default.
- W2993074870 date "2019-10-01" @default.
- W2993074870 modified "2023-09-26" @default.
- W2993074870 title "Optimizing Super Resolution for Face Recognition" @default.
- W2993074870 cites W1834627138 @default.
- W2993074870 cites W2034237167 @default.
- W2993074870 cites W2114770744 @default.
- W2993074870 cites W2126471044 @default.
- W2993074870 cites W2133665775 @default.
- W2993074870 cites W2145287260 @default.
- W2993074870 cites W2158698691 @default.
- W2993074870 cites W2183341477 @default.
- W2993074870 cites W2325939864 @default.
- W2993074870 cites W2331128040 @default.
- W2993074870 cites W2476548250 @default.
- W2993074870 cites W2503458650 @default.
- W2993074870 cites W2776107444 @default.
- W2993074870 cites W2952841512 @default.
- W2993074870 cites W2963466847 @default.
- W2993074870 cites W2963470893 @default.
- W2993074870 cites W2963583792 @default.
- W2993074870 cites W2963676087 @default.
- W2993074870 cites W2963839617 @default.
- W2993074870 cites W2964167901 @default.
- W2993074870 cites W2964325192 @default.
- W2993074870 cites W3101998545 @default.
- W2993074870 cites W54257720 @default.
- W2993074870 doi "https://doi.org/10.1109/sibgrapi.2019.00034" @default.
- W2993074870 hasPublicationYear "2019" @default.
- W2993074870 type Work @default.
- W2993074870 sameAs 2993074870 @default.
- W2993074870 citedByCount "4" @default.
- W2993074870 countsByYear W29930748702021 @default.
- W2993074870 countsByYear W29930748702023 @default.
- W2993074870 crossrefType "proceedings-article" @default.
- W2993074870 hasAuthorship W2993074870A5006191190 @default.
- W2993074870 hasAuthorship W2993074870A5045928378 @default.
- W2993074870 hasConcept C138268822 @default.
- W2993074870 hasConcept C144024400 @default.
- W2993074870 hasConcept C153180895 @default.
- W2993074870 hasConcept C154945302 @default.
- W2993074870 hasConcept C2779304628 @default.
- W2993074870 hasConcept C31510193 @default.
- W2993074870 hasConcept C31972630 @default.
- W2993074870 hasConcept C36289849 @default.
- W2993074870 hasConcept C41008148 @default.
- W2993074870 hasConceptScore W2993074870C138268822 @default.
- W2993074870 hasConceptScore W2993074870C144024400 @default.
- W2993074870 hasConceptScore W2993074870C153180895 @default.
- W2993074870 hasConceptScore W2993074870C154945302 @default.
- W2993074870 hasConceptScore W2993074870C2779304628 @default.
- W2993074870 hasConceptScore W2993074870C31510193 @default.
- W2993074870 hasConceptScore W2993074870C31972630 @default.
- W2993074870 hasConceptScore W2993074870C36289849 @default.
- W2993074870 hasConceptScore W2993074870C41008148 @default.
- W2993074870 hasLocation W29930748701 @default.
- W2993074870 hasOpenAccess W2993074870 @default.
- W2993074870 hasPrimaryLocation W29930748701 @default.
- W2993074870 hasRelatedWork W1548715306 @default.
- W2993074870 hasRelatedWork W1560697087 @default.
- W2993074870 hasRelatedWork W1989039360 @default.
- W2993074870 hasRelatedWork W2060029454 @default.
- W2993074870 hasRelatedWork W2100085003 @default.
- W2993074870 hasRelatedWork W2136485282 @default.
- W2993074870 hasRelatedWork W2146295394 @default.
- W2993074870 hasRelatedWork W2347601237 @default.
- W2993074870 hasRelatedWork W2545171730 @default.
- W2993074870 hasRelatedWork W2908959303 @default.
- W2993074870 isParatext "false" @default.
- W2993074870 isRetracted "false" @default.
- W2993074870 magId "2993074870" @default.
- W2993074870 workType "article" @default.