论文标题
抽象视觉推理的深度学习方法：对乌鸦进步矩阵的调查
Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices
论文作者
论文摘要
抽象的视觉推理（AVR）域涵盖了解决问题的问题，该问题需要能够推理给定场景中存在的实体之间的关系。尽管人类通常以“自然”的方式解决AVR任务，但即使没有先前的经验，这种类型的问题已被证明是当前机器学习系统的困难。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，作为研究机器智能的代理。我们专注于最常见的AVR任务类型 - Raven的渐进式矩阵（RPMS），并对应用于求解RPMS的学习方法和深层神经模型以及RPM基准集合提供了全面的回顾。对解决RPM的最新方法的绩效分析导致对该领域的当前和未来趋势的某些见解和评论。我们通过证明现实世界中的问题如何从RPM研究的发现中受益，从而结束了本文。
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.
