자료유형 | 학위논문 |
---|---|
서명/저자사항 | Learning to Learn for Small Sample Visual Recognition. |
개인저자 | Wang, Yu-Xiong. |
단체저자명 | Carnegie Mellon University. |
발행사항 | [S.l.]: Carnegie Mellon University., 2018. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2018. |
형태사항 | 206 p. |
기본자료 저록 | Dissertation Abstracts International 79-12B(E). Dissertation Abstract International |
ISBN | 9780438257733 |
학위논문주기 | Thesis (Ph.D.)--Carnegie Mellon University, 2018. |
일반주기 |
Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Adviser: Martial Hebert. |
요약 | Understanding how humans and machines recognize novel visual concepts from few examples remains a fundamental challenge. Humans are remarkably able to grasp a new concept and make meaningful generalization from just few examples. By contrast, st |
요약 | This dissertation aims to endow visual recognition systems with low-shot learning ability, so that they learn consistently well on data of different sample sizes. Our key insight is that the visual world is well structured and highly predictable |
요약 | We begin by learning from extremely limited data (e.g., one-shot learning). We cast the problem as supervised knowledge distillation and explore structures within model pairs. We introduce a meta-network that operates on the space of model param |
요약 | To further decouple a recognition model from ties to a specific set of categories, we introduce self-supervision using meta-data. We expose the model to a large amount of unlabeled real-world images through an unsupervised meta-training phase. B |
요약 | We them move on to learning from a medium sized number of examples and explore structures within an evolving model when learning from continuously changing data streams and tasks. We rethink the dominant knowledge transfer paradigm that fine-tun |
요약 | From a different perspective, humans can imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts and leveraging joint structures in both data and task spaces might help |
일반주제명 | Robotics. Artificial intelligence. Computer science. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |