Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels
Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels
复制标题
使用分层语言标签学习深度神经网络中的分层视觉表示
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
T. Griffiths
中科院分区：
文献类型：
--
作者：
Joshua C. Peterson;Paul Soulos;Aida Nematzadeh;T. Griffiths
现代卷积神经网络(CNN)能够在特定任务上达到人类水平的目标分类精度，并且在解释复杂的人类视觉表征方面优于竞争模型。然而，这些网络的分类问题与人类不同：这些网络的准确性是通过它们识别分配给每幅图像的单个标签的能力来评估的。这些标签经常随意地跨越自然的心理分类(例如，狗被分成不同的品种，但从未被联合归类为“狗”)，并对由此产生的表述产生偏见。相比之下，孩子们经常听到“狗”和“斑点狗”来描述相同的刺激，这有助于将感知上不同的物体(例如，品种)归入一个共同的心理类别。在这项工作中，我们为每个图像训练具有多个标签的CNN分类器，这些分类器对应于不同的抽象级别，并使用该框架来再现人类泛化行为中出现的经典模式。
Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations. However, the categorization problem is posed differently for these networks than for humans: the accuracy of these networks is evaluated by their ability to identify single labels assigned to each image. These labels often cut arbitrarily across natural psychological taxonomies (e.g., dogs are separated into breeds, but never jointly categorized as "dogs"), and bias the resulting representations. By contrast, it is common for children to hear both "dog" and "Dalmatian" to describe the same stimulus, helping to group perceptually disparate objects (e.g., breeds) into a common mental class. In this work, we train CNN classifiers with multiple labels for each image that correspond to different levels of abstraction, and use this framework to reproduce classic patterns that appear in human generalization behavior.