arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.04091cs.AIcs.CLcs.LG
收藏

抽象视觉推理的语言赋能

Abstract Visual Reasoning Enabled by Language

ETH Zürich(苏黎世联邦理工学院)

Giacomo Camposampiero, Loic Houmard, Benjamin Estermann, Joël Mathys, Roger Wattenhofer

AI总结:

本文提出一种基于学习的通用框架,通过将ARC任务从视觉转换到语言领域,利用预训练模型实现从手工先验到学习先验的转变,虽未超越最先进模型,但解决了部分此前未解任务。

摘要:

尽管人工智能(AI)模型在许多定义明确的应用中已取得人类甚至超人类的表现,但它们仍然难以展现出广泛而灵活的智能迹象。由François Chollet提出的抽象与推理语料库(ARC)是一个视觉智能基准,旨在评估AI系统与人类认知能力之间的接近程度。目前大多数方法依赖于精心手工设计的领域特定程序搜索,以暴力求解ARC中的任务。在本工作中,我们提出了一种基于学习的通用框架来解决ARC。该框架的核心是将任务从视觉领域转换到语言领域。这种语言与视觉的组合使得预训练模型能够在每个阶段被利用,从而实现了从手工设计的先验向模型学习到的先验的转变。虽然尚未在ARC上超越最先进的模型,但我们展示了我们方法的潜力,例如解决了一些先前未被解决的ARC任务。

英文摘要:

While artificial intelligence (AI) models have achieved human or even superhuman performance in many well-defined applications, they still struggle to show signs of broad and flexible intelligence. The Abstraction and Reasoning Corpus (ARC), a visual intelligence benchmark introduced by François Chollet, aims to assess how close AI systems are to human-like cognitive abilities. Most current approaches rely on carefully handcrafted domain-specific program searches to brute-force solutions for the tasks present in ARC. In this work, we propose a general learning-based framework for solving ARC. It is centered on transforming tasks from the vision to the language domain. This composition of language and vision allows for pre-trained models to be leveraged at each stage, enabling a shift from handcrafted priors towards the learned priors of the models. While not yet beating state-of-the-art models on ARC, we demonstrate the potential of our approach, for instance, by solving some ARC tasks that have not been solved previously.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑