서브메뉴
검색
Shape-Biased Representations for Object Category Recognition
Shape-Biased Representations for Object Category Recognition
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260209102903
- ISBN
- 9798263394059
- DDC
- 006
- 서명/저자
- Shape-Biased Representations for Object Category Recognition
- 발행사항
- [Sl] : Georgia Institute of Technology, 2023
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2023
- 형태사항
- 121 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
- 주기사항
- Advisor: Rehg, James M.;Hoffman, Judy.
- 학위논문주기
- Thesis (Ph.D.)--Georgia Institute of Technology, 2023.
- 초록/해제
- 요약While object recognition is a classical problem in computer vision that has witnessed incredible progress as a result of contemporary deep learning research, the key challenges of developing systems that can learn object categories from continually arriving data, from a few samples, and with limited supervision still remain. In this dissertation, we aim to borrow the learning strategy of shape bias and environmental bias of repetition, both of which are observed in young children, and apply them to continual, low-shot, and self-supervised learning of objects and object parts. In the continual learning domain, we demonstrate that repetition of learned concepts significantly ameliorates catastrophic forgetting. For low-shot learning we develop two methods for learning shape-biased object representations with decreasing supervision requirements: based on learning a joint image and 3D shape metric space from point clouds, and by self-supervised learning of object parts from multi-view pixel correspondences. We demonstrate that these methods of introducing a shape bias improve low-shot category recognition. Last, we find that contrastive learning from multi-view images allows for category-level part matching with performance competitive with baselines that have over 10 times more parameters, while being trained only on synthetic data. To support our investigations, we present two synthetic 3D object datasets, Toys200 and Toys4K, and develop a series of highly realistic synthetic data rendering systems that enable real-world generalization.
- 일반주제명
- Deep learning
- 일반주제명
- Failure analysis
- 일반주제명
- Computer vision
- 일반주제명
- School environment
- 일반주제명
- Toys
- 일반주제명
- Visualization
- 일반주제명
- Geometry
- 일반주제명
- Semantics
- 일반주제명
- Computer science
- 일반주제명
- Educational leadership
- 기본자료저록
- Dissertations Abstracts International. 87-05A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260203s2023 us c eng d■001000017365959
■00520260209102903
■006m o d
■007cr#unu||||||||
■020 ▼a9798263394059
■035 ▼a(MiAaPQ)AAI32315563
■035 ▼a(MiAaPQ)GeorgiaTech73115
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a006
■1001 ▼aStojanov, Stefan.
■24510▼aShape-Biased Representations for Object Category Recognition
■260 ▼a[Sl]▼bGeorgia Institute of Technology▼c2023
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2023
■300 ▼a121 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: A.
■500 ▼aAdvisor: Rehg, James M.;Hoffman, Judy.
■5021 ▼aThesis (Ph.D.)--Georgia Institute of Technology, 2023.
■520 ▼aWhile object recognition is a classical problem in computer vision that has witnessed incredible progress as a result of contemporary deep learning research, the key challenges of developing systems that can learn object categories from continually arriving data, from a few samples, and with limited supervision still remain. In this dissertation, we aim to borrow the learning strategy of shape bias and environmental bias of repetition, both of which are observed in young children, and apply them to continual, low-shot, and self-supervised learning of objects and object parts. In the continual learning domain, we demonstrate that repetition of learned concepts significantly ameliorates catastrophic forgetting. For low-shot learning we develop two methods for learning shape-biased object representations with decreasing supervision requirements: based on learning a joint image and 3D shape metric space from point clouds, and by self-supervised learning of object parts from multi-view pixel correspondences. We demonstrate that these methods of introducing a shape bias improve low-shot category recognition. Last, we find that contrastive learning from multi-view images allows for category-level part matching with performance competitive with baselines that have over 10 times more parameters, while being trained only on synthetic data. To support our investigations, we present two synthetic 3D object datasets, Toys200 and Toys4K, and develop a series of highly realistic synthetic data rendering systems that enable real-world generalization.
■590 ▼aSchool code: 0078.
■650 4▼aDeep learning
■650 4▼aFailure analysis
■650 4▼aComputer vision
■650 4▼aSchool environment
■650 4▼aToys
■650 4▼aVisualization
■650 4▼aGeometry
■650 4▼aSemantics
■650 4▼aComputer science
■650 4▼aEducational leadership
■650 4▼aEducational administration
■690 ▼a0800
■690 ▼a0984
■690 ▼a0449
■690 ▼a0514
■71020▼aGeorgia Institute of Technology.
■7730 ▼tDissertations Abstracts International▼g87-05A.
■790 ▼a0078
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365959▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


