DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Junmo | - |
dc.contributor.advisor | 김준모 | - |
dc.contributor.author | Jo, Minki | - |
dc.date.accessioned | 2021-05-13T19:42:05Z | - |
dc.date.available | 2021-05-13T19:42:05Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=947949&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/285211 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.8,[iii, 11 p. :] | - |
dc.description.abstract | In recent years, deep neural network (DNN) have achieved great success for various computer vision fields including image denoising. Unsupervised image denoising models that does not require a clean image outperforms the classical denoising methods. However, Current unsupervised denoiser still suffers from a serious problem that the denoised image looks blurry because denoisers cannot restore the clean edge of the images. This problem caused by the receptive field of the model takes less information from the noisy image. In this paper, we suggest a novel unsupervised denoising model by improving the learning algorithm. We adopt the ordinal regression task to the network which can supply more information of the input image. The proposed model outperforms the Noise2Self [3] on the benchmark datasets, such as Set12 and BSD68 [5] and Urban100. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep learning▼aImage Denoising▼aUnsupervised learning▼aSampling▼aNeural Network▼aOrdinal Regression | - |
dc.subject | 딥러닝▼a디노이징▼a비지도학습▼a샘플링▼a인공신경망 | - |
dc.title | Improving unsupervised image denoising via ordinal regression | - |
dc.title.alternative | 순차적 회귀 학습을 통한 비지도 이미지 디노이징 개선 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 조민기 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.