본문

서브메뉴

Tackling Bias Within Computer Vision Models- [electronic resource]
Tackling Bias Within Computer Vision Models - [electronic resource]
Tackling Bias Within Computer Vision Models- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100432
ISBN  
9798379718015
DDC  
004
저자명  
Ramaswamy, Vikram V.
서명/저자  
Tackling Bias Within Computer Vision Models - [electronic resource]
발행사항  
[S.l.]: : Princeton University., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(198 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
주기사항  
Advisor: Russakovsky, Olga.
학위논문주기  
Thesis (Ph.D.)--Princeton University, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Over the past decade the rapid increase in the ability of computer vision models has led to their applications in a variety of real-world applications from self-driving cars to medical diagnoses. However, there is increasing concern about the fairness and transparency of these models. In this thesis, we tackle these issue of bias within these models along two different axes.First, we consider the datasets that these models are trained on. We use two different methods to create a more balanced training dataset. First, we create a synthetic balanced dataset by sampling strategically from the latent space of a generative network. Next, we explore the potential of creating a dataset through a method other than scraping the internet: we solicit images from workers around the world, creating a dataset that is balanced across different geographical regions. Both techniques are shown to help create models with less bias.Second, we consider methods to improve interpretability of these models, which can then reveal potential biases within the model. We investigate a class of interpretability methods called concept-based methods that output explanations for models in terms of human understandable semantic concepts. We demonstrate the need for more careful development of the datasets used to learn the explanation as well as the concepts used within these explanations. We construct a new method that allows for users to select a trade-off between the understandability and faithfulness of the explanation. Finally, we discuss how methods that completely explain a model can be developed, and provide heuristics for the same.
일반주제명  
Computer science.
키워드  
Concept-based explanations
키워드  
ML systems
키워드  
Computer vision
키워드  
Medical diagnoses
키워드  
Real-world applications
기타저자  
Princeton University Computer Science
기본자료저록  
Dissertations Abstracts International. 84-12B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016932236
■00520240214100432
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379718015
■035    ▼a(MiAaPQ)AAI30490359
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aRamaswamy,  Vikram  V.
■24510▼aTackling  Bias  Within  Computer  Vision  Models▼h[electronic  resource]
■260    ▼a[S.l.]:▼bPrinceton  University.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(198  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  84-12,  Section:  B.
■500    ▼aAdvisor:  Russakovsky,  Olga.
■5021  ▼aThesis  (Ph.D.)--Princeton  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aOver  the  past  decade  the  rapid  increase  in  the  ability  of  computer  vision  models  has  led  to  their  applications  in  a  variety  of  real-world  applications  from  self-driving  cars  to  medical  diagnoses.  However,  there  is  increasing  concern  about  the  fairness  and  transparency  of  these  models.  In  this  thesis,  we  tackle  these  issue  of  bias  within  these  models  along  two  different  axes.First,  we  consider  the  datasets  that  these  models  are  trained  on.  We  use  two  different  methods  to  create  a  more  balanced  training  dataset.  First,  we  create  a  synthetic  balanced  dataset  by  sampling  strategically  from  the  latent  space  of  a  generative  network.  Next,  we  explore  the  potential  of  creating  a  dataset  through  a  method  other  than  scraping  the  internet:  we  solicit  images  from  workers  around  the  world,  creating  a  dataset  that  is  balanced  across  different  geographical  regions.  Both  techniques  are  shown  to  help  create  models  with  less  bias.Second,  we  consider  methods  to  improve  interpretability  of  these  models,  which  can  then  reveal  potential  biases  within  the  model.  We  investigate  a  class  of  interpretability  methods  called  concept-based  methods  that  output  explanations  for  models  in  terms  of  human  understandable  semantic  concepts.  We  demonstrate  the  need  for  more  careful  development  of  the  datasets  used  to  learn  the  explanation  as  well  as  the  concepts  used  within  these  explanations.  We  construct  a  new  method  that  allows  for  users  to  select  a  trade-off  between  the  understandability  and  faithfulness  of  the  explanation.  Finally,  we  discuss  how  methods  that  completely  explain  a  model  can  be  developed,  and  provide  heuristics  for  the  same.
■590    ▼aSchool  code:  0181.
■650  4▼aComputer  science.
■653    ▼aConcept-based  explanations
■653    ▼aML  systems
■653    ▼aComputer  vision
■653    ▼aMedical  diagnoses
■653    ▼aReal-world  applications
■690    ▼a0984
■690    ▼a0800
■71020▼aPrinceton  University▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g84-12B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0181
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16932236▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

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
    TF08158 전자도서 마이폴더 부재도서신고 비도서대출신청

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

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.