Tackling Bias Within Computer Vision Models- [electronic resource]
Tackling Bias Within Computer Vision Models- [electronic resource]
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214100432
- ISBN
- 9798379718015
- DDC
- 004
- 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
- ML systems
- 키워드
- Computer vision
- 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.