面向抽象视觉推理的深度学习方法：瑞文渐进矩阵综述
Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices
AI总结：
本文聚焦抽象视觉推理中的Raven's Progressive Matrices任务，综述了相关深度学习方法、模型及基准，分析前沿方法性能并提出领域趋势，展示了RPM研究对现实问题的价值。
摘要：
抽象视觉推理（AVR）领域涵盖的问题需要推理给定场景中实体间关系的能力才能解决。人类通常能以“自然”方式解决AVR任务，即便没有先前经验，而这类问题已被证明对当前机器学习系统而言颇具难度。本文总结了将深度学习方法应用于解决AVR问题的最新进展，以此作为研究机器智能的代理方向。我们聚焦于最常见的AVR任务类型——Raven's Progressive Matrices（瑞文渐进矩阵，RPMs），全面综述了用于解决RPM的学习方法、深度神经模型，以及RPM基准数据集。通过对解决RPM的前沿方法进行性能分析，我们提炼出关于该领域当前及未来趋势的若干洞见与评述。本文最后展示了现实世界问题如何从RPM研究的发现中获益。
英文摘要：
Abstract visual reasoning (AVR) domain encompasses problems solving which requires the ability to reason about relations among entities present in a given scene. While humans, generally, solve AVR tasks in a "natural" way, even without prior experience, this type of problems has proven difficult for current machine learning systems. The paper summarises recent progress in applying deep learning methods to solving AVR problems, as a proxy for studying machine intelligence. We focus on the most common type of AVR tasks -- the Raven's Progressive Matrices (RPMs) -- and provide a comprehensive review of the learning methods and deep neural models applied to solve RPMs, as well as, the RPM benchmark sets. Performance analysis of the state-of-the-art approaches to solving RPMs leads to formulation of certain insights and remarks on the current and future trends in this area. We conclude the paper by demonstrating how real-world problems can benefit from the discoveries of RPM studies.
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。
