paper-with-me

Papers

Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey

2023-12-27 · Jiaxing Huang, Jingyi Zhang, Kai Jiang, Han Qiu, Shijian Lu

Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions. To address them, Visual Instruction Tuning (VIT) has been intensively studied recently, which finetunes a large vision model with language as task instructions, aiming to learn from a wide range of vision tasks described by language instructions a general-purpose multimodal model that can follow arbitrary instructions and thus solve arbitrary tasks specified by the user. This work aims to provide a systematic review of visual instruction tuning, covering (1) the background that presents computer vision task paradigms and the development of VIT; (2) the foundations of VIT that introduce commonly used network architectures, visual instruction tuning frameworks and objectives, and evaluation setups and tasks; (3) the commonly used datasets in visual instruction tuning and evaluation; (4) the review of existing VIT methods that categorizes them with a taxonomy according to both the studied vision task and the method design and highlights the major contributions, strengths, and shortcomings of them; (5) the comparison and discussion of VIT methods over various instruction-following benchmarks; (6) several challenges, open directions and possible future works in visual instruction tuning research.

📄 PDF Abstract BibTeX arXiv:2312.16602

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction FollowingSurvey

Similar Papers 제목 키워드 기반

Visual Instruction Tuning

2023-04-17 · NeurIPS 2023 11 · Haotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae Lee

Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, w…

1 Image, 2*2 Stitching3D Question Answering (3D-QA)Image ClassificationImage Retrieval+9

Generative Visual Instruction Tuning

2024-06-17 · Jefferson Hernandez, Ruben Villegas, Vicente Ordonez

We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by cu…

Image GenerationImage-text matchingInstruction FollowingLanguage Modeling+4

When Parameter-efficient Tuning Meets General-purpose Vision-language Models

2023-12-16 · Yihang Zhai, Haixin Wang, Jianlong Chang, Xinlong Yang 외

Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applica…

Mixture-of-Experts

DuoGen: Towards General Purpose Interleaved Multimodal Generation

2026-01-31 · Min Shi, Xiaohui Zeng, Jiannan Huang, Yin Cui 외 arxiv

Interleaved multimodal generation enables capabilities beyond unimodal generation models, such as step-by-step instructional guides, visual planning, and generating visual drafts for reasoning. However, the quality of ex…

multimodal generationVideo GenerationImage Editing

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

2023-05-11 · NeurIPS 2023 11 · Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong 외

Large-scale pre-training and instruction tuning have been successful at creating general-purpose language models with broad competence. However, building general-purpose vision-language models is challenging due to the r…

1 Image, 2*2 StitchingDiversityImage RetrievalLong-Context Understanding+4