发表机构
National Institute of Advanced Industrial Science and Technology (AIST); Visual Geometry Group (VGG), University of Oxford; CADDi; OpenAI; University of Cambridge; University of Technology Nuremberg; University of Tsukuba; Google DeepMind; Carnegie Mellon University; New York University; Imperial College London; Harvard University; Stanford University; Princeton University(日本国立先进工业科学技术研究所(AIST); 牛津大学视觉几何组(VGG); CADDi公司; OpenAI公司; 剑桥大学; 纽伦堡工业大学; 筑波大学; 谷歌DeepMind; 卡内基梅隆大学; 纽约大学; 伦敦帝国学院; 哈佛大学; 斯坦福大学; 普林斯顿大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文以视觉为中心探讨通用人工智能(AGI)路径,提出视觉通用智能(VGI)概念,明确AGI时代计算机视觉的发展原则、模态、基准等关键方向。
AI 中文摘要
本文从以视觉为中心的视角重新审视智能,探究从视觉经验与学习中涌现的智能是否能为通用人工智能(AGI)提供一条可行路径。在语言领域,自Transformer架构问世以来,GPT系列模型通过在网页规模文本上进行自回归语言建模并辅以大规模扩展,已展现出对未见任务的迁移能力。这引发了一个自然的问题:从图像、视频、几何等视觉模态中能涌现出何种智能能力与形式?本文汇集了来自不同立场与机构的研究者,探讨视觉智能是否可作为通往AGI的路径,本文将其称为视觉通用智能(VGI)。本文的目标并非给出视觉智能的单一定义,而是阐明AGI时代计算机视觉应遵循的原则、视觉输入模态、基准、学习范式,以及以视觉为核心时与语言等其他模态的关系。
英文摘要
This paper reconsiders intelligence from a vision-centered perspective and examines whether intelligence emerging from visual experience and learning may provide a pathway toward AGI. In the language domain, beginning with the introduction of the Transformer architecture, the GPT series has demonstrated transfer to unseen tasks through autoregressive language modeling on web-scale text combined with aggressive scaling. This raises a natural question, namely, what capabilities and forms of intelligence can emerge from visual modalities such as images, videos, and geometry? In this paper, we discuss whether visual intelligence can serve as a pathway toward AGI, referred to in this paper as visual general intelligence (VGI), by bringing together contributors from diverse standpoints and affiliations. Our aim is not to offer a single definition of visual intelligence, but to clarify the principles that computer vision should pursue in the AGI era, the visual input modalities, the benchmarks, the learning paradigms, and the relationship between vision, when taken as the core, and other modalities such as language.