서브메뉴
검색
Unified Approaches for Multi-Task Vision-Language Interactions
Unified Approaches for Multi-Task Vision-Language Interactions
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152731
- ISBN
- 9798384027157
- DDC
- 401
- 저자명
- You, Haoxuan.
- 서명/저자
- Unified Approaches for Multi-Task Vision-Language Interactions
- 발행사항
- [Sl] : Columbia University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 123 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-02, Section: A.
- 주기사항
- Advisor: Chang, Shih-Fu.
- 학위논문주기
- Thesis (Ph.D.)--Columbia University, 2024.
- 초록/해제
- 요약Vision and Language are two major modalities that humans rely on to perceive the environment and understand the world. Recent advances in Artificial Intelligence (AI) facilitate the development of a variety of vision-language tasks derived from diverse multimodal interactions in daily life, such as image captioning, image-text matching, visual question answering (VQA), text-to-image generation, etc. Despite the remarkable performance, most previous state-of-the-art models are merely specialized for a single vision-language task, which lack generalizability across multiple tasks. Additionally, those specialized models sophisticate the algorithm designs and bring redundancy to model deployment when dealing with complex scenes.In this study, we investigate developing unified approaches capable of solving various vision-language interactions in a multi-task manner. We argue that unified multi-task methods could enjoy several potential advantages: (1) A unified framework for multiple tasks can reduce human efforts in designing different models for different tasks; (2) Reusing and sharing parameters across tasks can improve efficiency; (3) Some tasks may be complementary to other tasks so that multi-tasking can boost the performance; (4) They can deal with the complex tasks that need a joint collaborating of multiple basic tasks and enable new applications.In the first part of this thesis, we explore unified multi-task models with the goal of sharing and reusing as many parameters as possible between different tasks. We started with unifying many vision-language question-answering tasks, such as visual entailment, outside-knowledge VQA, and visual commonsense reasoning, in a simple iterative divide-and-conquer framework. Specifically, it iteratively decomposes the original text question into sub-question, solves each sub-question, and derives the answer to the original question, which can uniformly handle reasoning of various types and semantics levels within one framework. In the next work, we take one step further to unify tasks of image-to-text generation, text-to-image generation, vision-language understanding, and image-text matching all in one single large-scale Transformer-based model. The above two works demonstrate the feasibility, effectiveness and efficiency of sharing the parameters across different tasks in a single model. Nevertheless, they still need to switch between different tasks and can only conduct one task at a time.In the second part of this thesis, we introduce our efforts toward simultaneous multi-task models that can conduct multiple tasks at the same time with a single model. It has additional advantages: the model can learn to perform different tasks or combinations of multiple tasks automatically according to user queries; the joint interaction of tasks can enable new potential applications. We begin with compounding spatial understanding and semantic understanding in a single multimodal Transformer-based model. To enable models to understand and localize local regions, we proposed a hybrid region representation that seamlessly bridges regions with image and text. Coupled with a delicately collected training dataset, our model can perform joint spatial and semantic understanding at the same iteration, and empower a new application: spatial reasoning. Continuing the above project, we further introduce an effective module to encode the high-resolution images, and propose a pre-training method that aligns semantics and spatial understanding in high resolution. Besides, we also couple the Optical Character Recognition (OCR) capability together with spatial understanding in the model and study the techniques to improve the compatibility of various tasks.
- 일반주제명
- Linguistics
- 일반주제명
- Computer science
- 키워드
- Deep learning
- 키워드
- Multi-task
- 키워드
- Multimodal
- 키워드
- Vision-language
- 기타저자
- Columbia University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 86-02A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017163615
■00520250211152731
■006m o d
■007cr#unu||||||||
■020 ▼a9798384027157
■035 ▼a(MiAaPQ)AAI31490927
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a401
■1001 ▼aYou, Haoxuan.
■24510▼aUnified Approaches for Multi-Task Vision-Language Interactions
■260 ▼a[Sl]▼bColumbia University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a123 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-02, Section: A.
■500 ▼aAdvisor: Chang, Shih-Fu.
■5021 ▼aThesis (Ph.D.)--Columbia University, 2024.
■520 ▼aVision and Language are two major modalities that humans rely on to perceive the environment and understand the world. Recent advances in Artificial Intelligence (AI) facilitate the development of a variety of vision-language tasks derived from diverse multimodal interactions in daily life, such as image captioning, image-text matching, visual question answering (VQA), text-to-image generation, etc. Despite the remarkable performance, most previous state-of-the-art models are merely specialized for a single vision-language task, which lack generalizability across multiple tasks. Additionally, those specialized models sophisticate the algorithm designs and bring redundancy to model deployment when dealing with complex scenes.In this study, we investigate developing unified approaches capable of solving various vision-language interactions in a multi-task manner. We argue that unified multi-task methods could enjoy several potential advantages: (1) A unified framework for multiple tasks can reduce human efforts in designing different models for different tasks; (2) Reusing and sharing parameters across tasks can improve efficiency; (3) Some tasks may be complementary to other tasks so that multi-tasking can boost the performance; (4) They can deal with the complex tasks that need a joint collaborating of multiple basic tasks and enable new applications.In the first part of this thesis, we explore unified multi-task models with the goal of sharing and reusing as many parameters as possible between different tasks. We started with unifying many vision-language question-answering tasks, such as visual entailment, outside-knowledge VQA, and visual commonsense reasoning, in a simple iterative divide-and-conquer framework. Specifically, it iteratively decomposes the original text question into sub-question, solves each sub-question, and derives the answer to the original question, which can uniformly handle reasoning of various types and semantics levels within one framework. In the next work, we take one step further to unify tasks of image-to-text generation, text-to-image generation, vision-language understanding, and image-text matching all in one single large-scale Transformer-based model. The above two works demonstrate the feasibility, effectiveness and efficiency of sharing the parameters across different tasks in a single model. Nevertheless, they still need to switch between different tasks and can only conduct one task at a time.In the second part of this thesis, we introduce our efforts toward simultaneous multi-task models that can conduct multiple tasks at the same time with a single model. It has additional advantages: the model can learn to perform different tasks or combinations of multiple tasks automatically according to user queries; the joint interaction of tasks can enable new potential applications. We begin with compounding spatial understanding and semantic understanding in a single multimodal Transformer-based model. To enable models to understand and localize local regions, we proposed a hybrid region representation that seamlessly bridges regions with image and text. Coupled with a delicately collected training dataset, our model can perform joint spatial and semantic understanding at the same iteration, and empower a new application: spatial reasoning. Continuing the above project, we further introduce an effective module to encode the high-resolution images, and propose a pre-training method that aligns semantics and spatial understanding in high resolution. Besides, we also couple the Optical Character Recognition (OCR) capability together with spatial understanding in the model and study the techniques to improve the compatibility of various tasks.
■590 ▼aSchool code: 0054.
■650 4▼aLinguistics
■650 4▼aComputer science
■653 ▼aDeep learning
■653 ▼aMulti-task
■653 ▼aMultimodal
■653 ▼aVision-language
■653 ▼aVisual question answering
■690 ▼a0800
■690 ▼a0984
■690 ▼a0290
■71020▼aColumbia University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g86-02A.
■790 ▼a0054
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163615▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


