상세정보
Export to Refworks부가기능
Image Synthesis for Self-supervised Visual Representation Learning
상세 프로파일
| 자료유형 | 학위논문 |
|---|---|
| 서명/저자사항 | Image Synthesis for Self-supervised Visual Representation Learning. |
| 개인저자 | Zhang, Richard. |
| 단체저자명 | University of California, Berkeley. Electrical Engineering & Computer Sciences. |
| 발행사항 | [S.l.]: University of California, Berkeley., 2018. |
| 발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2018. |
| 형태사항 | 138 p. |
| 기본자료 저록 | Dissertation Abstracts International 80-01B(E). Dissertation Abstract International |
| ISBN | 9780438324800 |
| 학위논문주기 | Thesis (Ph.D.)--University of California, Berkeley, 2018. |
| 일반주기 |
Source: Dissertation Abstracts International, Volume: 80-01(E), Section: B.
Adviser: Alexei A. Efros. |
| 요약 | Deep networks are extremely adept at mapping a noisy, high-dimensional signal to a clean, low-dimensional target output (e.g., image classification). By solving this heavy compression task, the network also learns about natural image priors. How |
| 요약 | Part I describes the use of deep networks for conditional image synthesis. The section begins by exploring the problem of image colorization, proposing both automatic and user-guided approaches. This section then proposes a system for general im |
| 요약 | Part II explores the visual representations learned within deep networks. Colorization, as well as cross-channel prediction in general, is a simple but powerful pretext task for self-supervised learning. The representations from cross-channel pr |
| 일반주제명 | Artificial intelligence. Electrical engineering. Computer science. |
| 언어 | 영어 |
| 바로가기 | 
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
