자료유형 | 학위논문 |
---|---|
서명/저자사항 | Visual Understanding through Natural Language. |
개인저자 | Hendricks, Lisa Anne Marie. |
단체저자명 | University of California, Berkeley. Electrical Engineering & Computer Sciences. |
발행사항 | [S.l.]: University of California, Berkeley., 2019. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
형태사항 | 150 p. |
기본자료 저록 | Dissertations Abstracts International 81-04A. Dissertation Abstract International |
ISBN | 9781085792318 |
학위논문주기 | Thesis (Ph.D.)--University of California, Berkeley, 2019. |
일반주기 |
Source: Dissertations Abstracts International, Volume: 81-04, Section: A.
Advisor: Darrell, Trevor. |
이용제한사항 | This item must not be sold to any third party vendors. |
요약 | Powered by deep convolutional networks and large scale visual datasets, modern computer vision systems are capable of accurately recognizing thousands of visual categories. However, images contain much more than categorical labels: they contain information about where objects are located (in a forest or in a kitchen?), what attributes an object has (red or blue?), and how objects interact with other objects in a scene (is the child sitting on a sofa, or running in a field?). Natural language provides an efficient and intuitive way for visual systems to convey important information about a visual scene.We begin by considering a fundamental task as the intersection of language and vision: image captioning, in which a system receives an image as input and outputs a natural language sentence that describes the image. We consider two important shortcomings in modern image captioning models. First, in order to describe an object, like "otter", captioning models require pairs of sentences and images which include the object "otter". In Chapter 2, we build models that can learn an object like "otter" from classification data, which is abundant and easy to collect, then compose novel sentences at test time describing "otter", without any "otter" image caption examples at train time. Second, visual description models can be heavily driven by biases found in the training dataset. This can lead to object hallucination in which models hallucinate objects not present in an image. In Chapter 3, we propose tools to analyze language bias through the lens of object hallucination. Language bias can also lead to bias amplification |
일반주제명 | Artificial intelligence. Computer engineering. Linguistics. Electrical engineering. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |