DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 황성주 | - |
dc.contributor.author | Kang, SeongJae | - |
dc.contributor.author | 강성재 | - |
dc.date.accessioned | 2024-07-30T19:30:36Z | - |
dc.date.available | 2024-07-30T19:30:36Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096050&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321345 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2024.2,[iii, 27p. :] | - |
dc.description.abstract | With the advancements in Large Language Models (LLMs), a variety of Natural Language Processing(NLP) tasks can be effectively addressed using single unified LLM backbones. Notably, Instruction Tuning leverages the emergent abilities of LLMs by handling diverse language tasks through language instructions. However, in the field of computer vision, there is no single unified system capable of solving all types of computer vision tasks due to the inherent diversity of such tasks. In this paper, we propose an approach to address various computer vision tasks by utilizing the capabilities of visual instruction tuning. By unifying the model’s input and output as either text or image, we design a sequence-to- sequence modeling framework for computer vision tasks. In summary, we present a framework designed to solve any type of computer vision task—a universal computer vision task solver | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 멀티모달러닝▼a대형언어모델▼a기반모델▼a지시튜닝▼a시각지시튜닝▼a시퀸스-투-시퀸스 모델링▼a컴퓨터 비전 테스크 | - |
dc.subject | Multimodal learning▼aLarge language model▼aFoundation model▼aInstruction tuning▼aVisual instruction tuning▼aSequence-to-sequence modeling▼aComputer vision tasks | - |
dc.title | Toward universal computer vision task solver with single unified model | - |
dc.title.alternative | 단일 통합 모델을 통해 범용적인 컴퓨터 비전 테스크들을 풀기 위한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Hwang, Sung Ju | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.