Same-different conceptualization: a machine vision perspective
Same-different conceptualization: a machine vision perspective
复制标题
DOI：
10.1016/j.cobeha.2020.08.008
复制
发表时间：
2021-02-01
影响因子：
5
通讯作者：
Serre, Thomas
中科院分区：
文献类型：
--
作者：
Ricci, Matthew;Cadene, Remi;Serre, Thomas
本综述的目的是将认知心理学的材料与最近的机器视觉研究结合起来，以确定视觉同异辨别和关系理解的合理神经机制。我们强调人工神经网络研究的发展如何提供计算证据，表明注意力和工作记忆在确定视觉关系（包括同异关系）中的作用。我们回顾了最近一些将这些机制纳入灵活的视觉推理模型的尝试。特别关注最近在视觉和语言信息上联合训练的模型。这些最新的系统很有希望，但它们在几个方面仍然达不到生物学标准，我们将在最后一节中概述。
The goal of this review is to bring together material from cognitive psychology with recent machine vision studies to identify plausible neural mechanisms for visual same-different discrimination and relational understanding. We highlight how developments in the study of artificial neural networks provide computational evidence implicating attention and working memory in the ascertaining of visual relations, including same-different relations. We review some recent attempts to incorporate these mechanisms into flexible models of visual reasoning. Particular attention is given to recent models jointly trained on visual and linguistic information. These recent systems are promising, but they still fall short of the biological standard in several ways, which we outline in a final section.