DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 이동만 | - |
dc.contributor.author | Kim, Youngrae | - |
dc.contributor.author | 김영래 | - |
dc.date.accessioned | 2024-07-30T19:31:45Z | - |
dc.date.available | 2024-07-30T19:31:45Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1097261&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321681 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2024.2,[iv, 22 p. :] | - |
dc.description.abstract | Real-world vision tasks frequently suffer from the appearance of adverse weather conditions including rain, fog, snow, and raindrops in captured images. Recently, several generic methods for restoring weather-degraded images have been proposed, aiming to remove multiple types of adverse weather effects present in the images. However, these methods have considered weather as discrete and mutually exclusive variables, leading to failure in generalizing to unforeseen weather conditions beyond the scope of the training data, such as the co-occurrence of rain, fog, and raindrops. To this end, weather-degraded image restoration models should have flexible adaptability to the current unknown weather condition to ensure reliable and optimal performance. The adaptation method should also be able to cope with data scarcity for real-world adaptation. This paper proposes MetaWeather, a few-shot weather-degraded image restoration method for arbitrary weather conditions. For this, we devise the core piece of MetaWeather, coined Degradation Pattern Matching Module (DPMM), which leverages representations from a few-shot support set by matching features between input and sample images under new weather conditions. In addition, we build meta-knowledge with episodic meta-learning on top of our MetaWeather architecture to provide flexible adaptability. In the meta-testing phase, we adopt a parameter-efficient fine-tuning method to preserve the prebuilt knowledge and avoid the overfitting problem. Experiments on the BID Task II.A dataset show our method achieves the best performance on PSNR and SSIM compared to state-of-the-art image restoration methods. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 컴퓨터 비젼▼a도메인 적응▼a퓨샷 학습▼a메타 학습▼a이미지 복원 | - |
dc.subject | Computer vision▼aDomain adaptation▼aFew-shot learning▼aMeta learning▼aImage restoration | - |
dc.title | Few-shot weather-degraded image restoration | - |
dc.title.alternative | 날씨로 인한 저품질 이미지 복원 모델의 퓨샷 적응 기법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | Lee, Dongman | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.