Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048798122> ?p ?o ?g. }
- W3048798122 abstract "Recently, deep learning approaches have been extensively studied for low-dose CT denoising thanks to its superior performance despite the fast computational time. In particular, cycleGAN has been demonstrated as a powerful unsupervised learning scheme to improve the low-dose CT image quality without requiring matched high-dose reference data. Unfortunately, one of the main limitations of the cycleGAN approach is that it requires two deep neural network generators at the training phase, although only one of them is used at the inference phase. The secondary auxiliary generator is needed to enforce the cycle-consistency, but the additional memory requirement and increases of the learnable parameters are the main huddles for cycleGAN training. To address this issue, here we propose a novel cycleGAN architecture using a single switchable generator. In particular, a single generator is implemented using adaptive instance normalization (AdaIN) layers so that the baseline generator converting a low-dose CT image to a routine-dose CT image can be switched to a generator converting high-dose to low-dose by simply changing the AdaIN code. Thanks to the shared baseline network, the additional memory requirement and weight increases are minimized, and the training can be done more stably even with small training data. Experimental results show that the proposed method outperforms the previous cycleGAN approaches while using only about half the parameters." @default.
- W3048798122 created "2020-08-18" @default.
- W3048798122 creator A5012644755 @default.
- W3048798122 creator A5030881632 @default.
- W3048798122 date "2020-08-13" @default.
- W3048798122 modified "2023-09-25" @default.
- W3048798122 title "AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising" @default.
- W3048798122 cites W1522301498 @default.
- W3048798122 cites W1533861849 @default.
- W3048798122 cites W1901129140 @default.
- W3048798122 cites W1963504323 @default.
- W3048798122 cites W1975756786 @default.
- W3048798122 cites W1999320095 @default.
- W3048798122 cites W2083927153 @default.
- W3048798122 cites W2096605619 @default.
- W3048798122 cites W2099471712 @default.
- W3048798122 cites W2133665775 @default.
- W3048798122 cites W2135627045 @default.
- W3048798122 cites W2158242620 @default.
- W3048798122 cites W2163605009 @default.
- W3048798122 cites W2476548250 @default.
- W3048798122 cites W2502312327 @default.
- W3048798122 cites W2508457857 @default.
- W3048798122 cites W2584483805 @default.
- W3048798122 cites W2593414223 @default.
- W3048798122 cites W2603777577 @default.
- W3048798122 cites W2617128058 @default.
- W3048798122 cites W2743780012 @default.
- W3048798122 cites W2793477525 @default.
- W3048798122 cites W2795777276 @default.
- W3048798122 cites W2887746098 @default.
- W3048798122 cites W2947111506 @default.
- W3048798122 cites W2951997238 @default.
- W3048798122 cites W2962770929 @default.
- W3048798122 cites W2962793481 @default.
- W3048798122 cites W2963073614 @default.
- W3048798122 cites W2974967908 @default.
- W3048798122 cites W3007811546 @default.
- W3048798122 cites W3104324122 @default.
- W3048798122 cites W385466589 @default.
- W3048798122 doi "https://doi.org/10.48550/arxiv.2008.05753" @default.
- W3048798122 hasPublicationYear "2020" @default.
- W3048798122 type Work @default.
- W3048798122 sameAs 3048798122 @default.
- W3048798122 citedByCount "2" @default.
- W3048798122 countsByYear W30487981222020 @default.
- W3048798122 countsByYear W30487981222021 @default.
- W3048798122 crossrefType "posted-content" @default.
- W3048798122 hasAuthorship W3048798122A5012644755 @default.
- W3048798122 hasAuthorship W3048798122A5030881632 @default.
- W3048798122 hasBestOaLocation W30487981221 @default.
- W3048798122 hasConcept C108583219 @default.
- W3048798122 hasConcept C111335779 @default.
- W3048798122 hasConcept C115961682 @default.
- W3048798122 hasConcept C121332964 @default.
- W3048798122 hasConcept C136886441 @default.
- W3048798122 hasConcept C144024400 @default.
- W3048798122 hasConcept C153180895 @default.
- W3048798122 hasConcept C154945302 @default.
- W3048798122 hasConcept C163258240 @default.
- W3048798122 hasConcept C163294075 @default.
- W3048798122 hasConcept C177264268 @default.
- W3048798122 hasConcept C19165224 @default.
- W3048798122 hasConcept C199360897 @default.
- W3048798122 hasConcept C2524010 @default.
- W3048798122 hasConcept C2776214188 @default.
- W3048798122 hasConcept C2776436953 @default.
- W3048798122 hasConcept C2776760102 @default.
- W3048798122 hasConcept C2780992000 @default.
- W3048798122 hasConcept C33923547 @default.
- W3048798122 hasConcept C41008148 @default.
- W3048798122 hasConcept C50644808 @default.
- W3048798122 hasConcept C62520636 @default.
- W3048798122 hasConceptScore W3048798122C108583219 @default.
- W3048798122 hasConceptScore W3048798122C111335779 @default.
- W3048798122 hasConceptScore W3048798122C115961682 @default.
- W3048798122 hasConceptScore W3048798122C121332964 @default.
- W3048798122 hasConceptScore W3048798122C136886441 @default.
- W3048798122 hasConceptScore W3048798122C144024400 @default.
- W3048798122 hasConceptScore W3048798122C153180895 @default.
- W3048798122 hasConceptScore W3048798122C154945302 @default.
- W3048798122 hasConceptScore W3048798122C163258240 @default.
- W3048798122 hasConceptScore W3048798122C163294075 @default.
- W3048798122 hasConceptScore W3048798122C177264268 @default.
- W3048798122 hasConceptScore W3048798122C19165224 @default.
- W3048798122 hasConceptScore W3048798122C199360897 @default.
- W3048798122 hasConceptScore W3048798122C2524010 @default.
- W3048798122 hasConceptScore W3048798122C2776214188 @default.
- W3048798122 hasConceptScore W3048798122C2776436953 @default.
- W3048798122 hasConceptScore W3048798122C2776760102 @default.
- W3048798122 hasConceptScore W3048798122C2780992000 @default.
- W3048798122 hasConceptScore W3048798122C33923547 @default.
- W3048798122 hasConceptScore W3048798122C41008148 @default.
- W3048798122 hasConceptScore W3048798122C50644808 @default.
- W3048798122 hasConceptScore W3048798122C62520636 @default.
- W3048798122 hasLocation W30487981221 @default.
- W3048798122 hasOpenAccess W3048798122 @default.
- W3048798122 hasPrimaryLocation W30487981221 @default.
- W3048798122 hasRelatedWork W1863050261 @default.
- W3048798122 hasRelatedWork W2016839265 @default.