서브메뉴
검색
Robust and Efficient Deep Learning for Multimedia Generation and Recognition- [electronic resource]
Robust and Efficient Deep Learning for Multimedia Generation and Recognition- [electronic resource]
상세정보
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214101209
- ISBN
- 9798380362153
- DDC
- 621.3
- 서명/저자
- Robust and Efficient Deep Learning for Multimedia Generation and Recognition - [electronic resource]
- 발행사항
- [S.l.]: : University of California, San Diego., 2023
- 발행사항
- Ann Arbor : : ProQuest Dissertations & Theses,, 2023
- 형태사항
- 1 online resource(289 p.)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
- 주기사항
- Advisor: Koushanfar, Farinaz.
- 학위논문주기
- Thesis (Ph.D.)--University of California, San Diego, 2023.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 초록/해제
- 요약Deep Neural Networks (DNNs) have transformed the field of multimedia generation and recognition by replacing traditional hand-engineered systems in domains like vision, speech and text. This is because DNNs can operate end-to-end and model complex dependencies yielding state-of-the-art results on several generation and recognition benchmarks. However, there are three key challenges that need to be addressed for the practical, secure and reliable deployment of DNN-based media processing systems: 1) Robustness: DNNs are vulnerable to adversarial attacks, 2) Data-Requirement: DNNs often require large amounts of labelled data, 3) Compute-Efficiency: DNNs require extensive compute and resources.My research focuses on addressing the above three challenges of DNN based multimedia generation and recognition systems. On the robustness side, I first analyze practical vulnerabilities of DNN-based recognition systems and then propose a robust defense framework that can reliably identify adversarial inputs using perceptually informed input transformations. To address the challenge of data-requirement, I develop training frameworks that can effectively adapt foundation models trained using self-supervised learning for recognition and synthesis tasks in a data-efficient manner. Finally, to address the challenge of compute-efficiency, I propose acceleration methods using hardware-software codesign that significantly reduce the latency and resource-requirement while preserving the synthesis quality of DNN generators.
- 일반주제명
- Computer engineering.
- 일반주제명
- Electrical engineering.
- 키워드
- Deep learning
- 기타저자
- University of California, San Diego Electrical and Computer Engineering
- 기본자료저록
- Dissertations Abstracts International. 85-03B.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008240612s2023 us |||||||||||||||c||eng d■001000016933147
■00520240214101209
■006m o d
■007cr#unu||||||||
■020 ▼a9798380362153
■035 ▼a(MiAaPQ)AAI30525337
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a621.3
■1001 ▼aHussain, Shehzeen Samarah.
■24510▼aRobust and Efficient Deep Learning for Multimedia Generation and Recognition▼h[electronic resource]
■260 ▼a[S.l.]:▼bUniversity of California, San Diego. ▼c2023
■260 1▼aAnn Arbor :▼bProQuest Dissertations & Theses, ▼c2023
■300 ▼a1 online resource(289 p.)
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-03, Section: B.
■500 ▼aAdvisor: Koushanfar, Farinaz.
■5021 ▼aThesis (Ph.D.)--University of California, San Diego, 2023.
■506 ▼aThis item must not be sold to any third party vendors.
■520 ▼aDeep Neural Networks (DNNs) have transformed the field of multimedia generation and recognition by replacing traditional hand-engineered systems in domains like vision, speech and text. This is because DNNs can operate end-to-end and model complex dependencies yielding state-of-the-art results on several generation and recognition benchmarks. However, there are three key challenges that need to be addressed for the practical, secure and reliable deployment of DNN-based media processing systems: 1) Robustness: DNNs are vulnerable to adversarial attacks, 2) Data-Requirement: DNNs often require large amounts of labelled data, 3) Compute-Efficiency: DNNs require extensive compute and resources.My research focuses on addressing the above three challenges of DNN based multimedia generation and recognition systems. On the robustness side, I first analyze practical vulnerabilities of DNN-based recognition systems and then propose a robust defense framework that can reliably identify adversarial inputs using perceptually informed input transformations. To address the challenge of data-requirement, I develop training frameworks that can effectively adapt foundation models trained using self-supervised learning for recognition and synthesis tasks in a data-efficient manner. Finally, to address the challenge of compute-efficiency, I propose acceleration methods using hardware-software codesign that significantly reduce the latency and resource-requirement while preserving the synthesis quality of DNN generators.
■590 ▼aSchool code: 0033.
■650 4▼aComputer engineering.
■650 4▼aElectrical engineering.
■653 ▼aDeep Neural Networks
■653 ▼aMultimedia generation
■653 ▼aRecognition systems
■653 ▼aDeep learning
■690 ▼a0464
■690 ▼a0800
■690 ▼a0544
■71020▼aUniversity of California, San Diego▼bElectrical and Computer Engineering.
■7730 ▼tDissertations Abstracts International▼g85-03B.
■773 ▼tDissertation Abstract International
■790 ▼a0033
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16933147▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202402▼f2024
