Common object representations for visual production and recognition
Common object representations for visual production and recognition
复制标题
DOI：
10.1101/097840
复制
发表时间：
2017-01
期刊：
影响因子：
--
通讯作者：
Judith E. Fan;Daniel L. K. Yamins;N. Turk-Browne
中科院分区：
文献类型：
--
作者：
Judith E. Fan;Daniel L. K. Yamins;N. Turk-Browne
语言的产生和理解一直被认为是语言不可分割的组成部分。相比之下，对视觉的研究几乎完全集中在理解上。在这里，我们研究绘画-视觉生产的最基本形式。我们如何以视觉形式传达概念，以及如何改进这种技能，进而影响识别？我们开发了一个在线平台来收集大量的绘画和识别数据，并应用了一个只在自然图像上训练的视觉皮层的深度卷积神经网络模型来探索绘画招募支持自然视觉对象识别的相同抽象特征表示的假设。与这一假设相一致的是，该模型的更高层次捕捉了对识别最重要的绘画和自然图像的抽象特征，并且学习生成更可识别的对象绘画的人表现出对这些对象的增强识别。这些发现可以解释为什么绘画对于传达视觉概念如此有效，它们提出了评估和精炼概念知识的新方法，并强调了深度网络在理解人类学习方面的潜力。
Production and comprehension have long been viewed as inseparable components of language. The study of vision, by contrast, has centered almost exclusively on comprehension. Here we investigate drawing — the most basic form of visual production. How do we convey concepts in visual form, and how does refining this skill, in turn, affect recognition? We developed an online platform for collecting large amounts of drawing and recognition data, and applied a deep convolutional neural network model of visual cortex trained only on natural images to explore the hypothesis that drawing recruits the same abstract feature representations that support natural visual object recognition. Consistent with this hypothesis, higher layers of this model captured the abstract features of both drawings and natural images most important for recognition, and people learning to produce more recognizable drawings of objects exhibited enhanced recognition of those objects. These findings could explain why drawing is so effective for communicating visual concepts, they suggest novel approaches for evaluating and refining conceptual knowledge, and they highlight the potential of deep networks for understanding human learning.