Huang Taicheng, Zhen Zonglei, Liu Jia
State Key Laboratory of Cognitive Neuroscience and Learning and IDG/McGovern Institute for Brain Research, Beijing Normal University, Beijing, China.
Beijing Key Laboratory of Applied Experimental Psychology, Faculty of Psychology, Beijing Normal University, Beijing, China.
Front Comput Neurosci. 2021 Feb 22;15:625804. doi: 10.3389/fncom.2021.625804. eCollection 2021.
Human not only can effortlessly recognize objects, but also characterize object categories into semantic concepts with a nested hierarchical structure. One dominant view is that top-down conceptual guidance is necessary to form such hierarchy. Here we challenged this idea by examining whether deep convolutional neural networks (DCNNs) could learn relations among objects purely based on bottom-up perceptual experience of objects through training for object categorization. Specifically, we explored representational similarity among objects in a typical DCNN (e.g., AlexNet), and found that representations of object categories were organized in a hierarchical fashion, suggesting that the relatedness among objects emerged automatically when learning to recognize them. Critically, the emerged relatedness of objects in the DCNN was highly similar to the WordNet in human, implying that top-down conceptual guidance may not be a prerequisite for human learning the relatedness among objects. In addition, the developmental trajectory of the relatedness among objects during training revealed that the hierarchical structure was constructed in a coarse-to-fine fashion, and evolved into maturity before the establishment of object recognition ability. Finally, the fineness of the relatedness was greatly shaped by the demand of tasks that the DCNN performed, as the higher superordinate level of object classification was, the coarser the hierarchical structure of the relatedness emerged. Taken together, our study provides the first empirical evidence that semantic relatedness of objects emerged as a by-product of object recognition in DCNNs, implying that human may acquire semantic knowledge on objects without explicit top-down conceptual guidance.
人类不仅能够轻松识别物体，还能将物体类别表征为具有嵌套层次结构的语义概念。一种主流观点认为，自上而下的概念引导对于形成这种层次结构是必要的。在这里，我们通过研究深度卷积神经网络（DCNN）是否可以通过物体分类训练，纯粹基于物体的自下而上的感知经验来学习物体之间的关系，对这一观点提出了挑战。具体来说，我们探索了典型DCNN（如AlexNet）中物体之间的表征相似性，发现物体类别的表征是以层次方式组织的，这表明在学习识别物体时，物体之间的相关性会自动出现。至关重要的是，DCNN中出现的物体相关性与人类的WordNet高度相似，这意味着自上而下的概念引导可能不是人类学习物体之间相关性的先决条件。此外，训练过程中物体相关性的发展轨迹表明，层次结构是以从粗到细的方式构建的，并在物体识别能力建立之前发展成熟。最后，相关性的精细程度很大程度上受到DCNN执行任务需求的影响，物体分类的上级层次越高，相关性的层次结构就越粗。综上所述，我们的研究提供了首个实证证据，表明物体的语义相关性是DCNN中物体识别的副产品，这意味着人类可能在没有明确的自上而下概念引导的情况下获取关于物体的语义知识。
