본문

서브메뉴

Visual Intelligence Beyond Human Supervision
Visual Intelligence Beyond Human Supervision
Visual Intelligence Beyond Human Supervision

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103608
ISBN  
9798293892341
DDC  
004
저자명  
Wang, XuDong.
서명/저자  
Visual Intelligence Beyond Human Supervision
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
231 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-04, Section: B.
주기사항  
Advisor: Darrell, Trevor.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Achieving artificial general intelligence requires developing models capable of perceiving, understanding, and interacting with the world across diverse sensory modalities-beyond the confines of language alone. While self-supervised learning has enabled remarkable advances in large language models (LLMs), replicating this success in the visual domain remains a significant challenge, largely due to the continued reliance on human-annotated data. This dissertation explores how self-supervised learning can unlock visual intelligence beyond human supervision, enabling models to learn directly from the inherent structure and regularities of the visual world.The thesis presents a series of efforts aimed at advancing this vision. First, it investigates self-supervised visual world understanding, demonstrating that models can achieve strong segmentation performance without the billions of labeled masks used in supervised approaches such as the Segment Anything Model (SAM). Instead, our work shows that models can "segment anything'' by leveraging the rich semantics present in unlabeled data. Second, it introduces methods that unify generative and discriminative visual models through self-supervision and synthetic data, allowing these systems to complement one another and improve both visual understanding and generation. Third, the dissertation examines how to build robust visual models through self-supervised debiased learning, proposing techniques that mitigate bias and enhance generalization under imperfect data conditions, within a data-centric representation learning framework.Together, these contributions serve a common goal: building scalable, multi-modality visual intelligence that learn not by mimicking human annotations, but by discovering the latent structure of the world itself!
일반주제명  
Computer science
일반주제명  
Electrical engineering
키워드  
Large language models
키워드  
Segment Anything Model
키워드  
Human-annotated data
기타저자  
University of California, Berkeley Electrical Engineering & Computer Sciences
기본자료저록  
Dissertations Abstracts International. 87-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357849
■00520260202103608
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798293892341
■035    ▼a(MiAaPQ)AAI32043020
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aWang,  XuDong.
■24510▼aVisual  Intelligence  Beyond  Human  Supervision
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a231  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-04,  Section:  B.
■500    ▼aAdvisor:  Darrell,  Trevor.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aAchieving  artificial  general  intelligence  requires  developing  models  capable  of  perceiving,  understanding,  and  interacting  with  the  world  across  diverse  sensory  modalities-beyond  the  confines  of  language  alone.  While  self-supervised  learning  has  enabled  remarkable  advances  in  large  language  models  (LLMs),  replicating  this  success  in  the  visual  domain  remains  a  significant  challenge,  largely  due  to  the  continued  reliance  on  human-annotated  data.  This  dissertation  explores  how  self-supervised  learning  can  unlock  visual  intelligence  beyond  human  supervision,  enabling  models  to  learn  directly  from  the  inherent  structure  and  regularities  of  the  visual  world.The  thesis  presents  a  series  of  efforts  aimed  at  advancing  this  vision.  First,  it  investigates  self-supervised  visual  world  understanding,  demonstrating  that  models  can  achieve  strong  segmentation  performance  without  the  billions  of  labeled  masks  used  in  supervised  approaches  such  as  the  Segment  Anything  Model  (SAM).  Instead,  our  work  shows  that  models  can  "segment  anything''  by  leveraging  the  rich  semantics  present  in  unlabeled  data.  Second,  it  introduces  methods  that  unify  generative  and  discriminative  visual  models  through  self-supervision  and  synthetic  data,  allowing  these  systems  to  complement  one  another  and  improve  both  visual  understanding  and  generation.  Third,  the  dissertation  examines  how  to  build  robust  visual  models  through  self-supervised  debiased  learning,  proposing  techniques  that  mitigate  bias  and  enhance  generalization  under  imperfect  data  conditions,  within  a  data-centric  representation  learning  framework.Together,  these  contributions  serve  a  common  goal:  building  scalable,  multi-modality  visual  intelligence  that  learn  not  by  mimicking  human  annotations,  but  by  discovering  the  latent  structure  of  the  world  itself!
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science
■650  4▼aElectrical  engineering
■653    ▼aLarge  language  models
■653    ▼aSegment  Anything  Model
■653    ▼aHuman-annotated  data
■690    ▼a0800
■690    ▼a0984
■690    ▼a0544
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g87-04B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357849▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF14872 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.