DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 주재걸 | - |
dc.contributor.author | Park, Yeo Jeong | - |
dc.contributor.author | 박여정 | - |
dc.date.accessioned | 2024-07-25T19:30:46Z | - |
dc.date.available | 2024-07-25T19:30:46Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1045728&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320540 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.8,[iv, 26 p. :] | - |
dc.description.abstract | Video-to-video translation aims to generate video frames of a target domain from an input video. Despite its usefulness, the existing video-to-video translation methods require enormous computations, necessitating their model compression for wide use. While there exist compression methods that improve computational efficiency in various image/video tasks, a generally-applicable compression method for video-to-video translation has not been studied much. In response, this paper presents Shortcut-V2V, a general-purpose compression framework for video-to-video translation. Shortcut-V2V avoids full inference for every neighboring video frame by approximating the intermediate features of a current frame from those of the preceding frame. Moreover, in our framework, a newly-proposed block called AdaBD adaptively blends and deforms features of neighboring frames, which makes more accurate predictions of the intermediate features possible. We conduct quantitative and qualitative evaluations using well-known video-to-video translation models on various tasks to demonstrate the general applicability of our framework. The results show that Shortcut-V2V achieves comparable performance compared to the original video-to-video translation model while saving 3.2-5.7 times computational cost and 7.8-44 times memory at test time. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 비디오 변환▼a효율적인 딥러닝▼a모델 압축▼a시간 축의 정보 중복성▼a비디오 생성 모델 | - |
dc.subject | Video-to-video translation▼aEfficient deep learning▼aModel compression▼aTemporal redundancy▼aVideo generative model | - |
dc.title | (A) compression framework for video-to-video translation based on temporal redundancy reduction | - |
dc.title.alternative | 시간 축의 중복 정보 제거를 기반으로 한 비디오 변환 모델 압축 기술 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Choo, Jaegul | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.