DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Park, HyunWook | - |
dc.contributor.advisor | 박현욱 | - |
dc.contributor.author | Park, Seokjun | - |
dc.date.accessioned | 2021-05-13T19:39:57Z | - |
dc.date.available | 2021-05-13T19:39:57Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=925253&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/285089 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.8,[iii, 41 p. :] | - |
dc.description.abstract | In this work, we propose contrastive learning based deep neural network model for no-reference image quality assessment (NR-IQA). The proposed deep neural network model consists of 11convolutional neural networks (CNN) in parallel, each CNN initializing the weight to extract the characteristics of a specific group. For the initialization of weights of 11 CNNs, 11 groups are generated from LIVE dataset. The 11 groups are divided based on the distortion types and subjective image quality scores of the dataset, and the data in each group do not need to be mutually exclusive. With 11 groups generated from the dataset, 11 siamese networks that extract the characteristics of each group are pre-trained through contrastive learning. We then fine-tune the entire network on the target subjective image quality score. This method shows better performance than the previous NR-IQA model by using only limited image quality assessment data and suggests a feature extraction method that is meaningful for image quality assessment. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | No-reference image quality assessment▼aContrastive learning▼aSiamese network▼aConvolutional neural network | - |
dc.subject | 비참조 영상 화질 평가▼a대조적 학습▼a샴 네트워크▼a컨볼루션 신경망 | - |
dc.title | Contrastive learning based deep neural network for no-reference image quality assessment | - |
dc.title.alternative | 비참조 영상 화질 평가를 위한 대조적 학습 기반의 심층 신경망 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 박석준 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.