深层卷积神经网络对面部配置敏感.
Virginia E Strehle1,2,3, Natalie K Bendiksen1,4,5, Alice J O'Toole1,6,7
1School of Behavioral and Brain Sciences, The University of Texas at Dallas, Dallas, Texas, USA.
Journal of vision
|November 5, 2024
概括
深层卷积神经网络 (DCNNs) 对面部配置变化表现出敏感性,类似于人类面部识别. 这些模型优先考虑配置信息,而不是用于识别面部的特征细节.
科学领域:
- 计算机视觉 计算机视觉
- 认知神经科学 认知神经科学
- 人工智能的人工智能
背景情况:
- 深度卷积神经网络 (DCNNs) 在面部识别任务中实现高精度.
- 人类的面部识别在很大程度上依赖于对面部配置的敏感性.
- 目前尚不清楚DCNN是否会发展出类似人类的面部表现.
研究的目的:
- 调查受过面部识别培训的DCNN是否会感知面部特征和配置的变化.
- 为了比较DCNN表示对配置和特征变化的灵敏度.
- 为了确定DCNN的配置灵敏性是否来自图像属性或网络处理.
主要方法:
- 通过改变眼睛或鼻子口腔之间的距离来改变面部配置.
- 通过在不同面孔之间交换眼睛或嘴巴来改变面部特征.
- 通过两个DCNN模型处理改变的面部 (Ranjan等, 2018; Szegedy等, 2017) 并比较表示相似性.
主要成果:
- 两个DCNN都对配置和功能更改表现出了敏感性.
- 配置更改对DCNN表示有更大的影响,而不是功能更改.
- 对配置的灵敏度从像素级增加到DCNN编码,而功能灵敏度保持不变.
结论:
- DCNN对面部配置敏感,反映了人类的感知.
- 在DCNN中对配置的增强敏感性是网络处理的结果,而不仅仅是图像属性.
- 配置信息对于DCNN歧视相似的面孔至关重要,这可能是由于培训目标.
相关概念视频
Association Areas of the Cortex
5.1K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
5.1K
Prosopagnosia
142
Prosopagnosia, also known as face blindness, is the inability to recognize faces. In severe cases, individuals with prosopagnosia may not recognize close family members, including parents and spouses, by their faces. For instance, someone with prosopagnosia might walk past their child in a crowd, only realizing their mistake upon noticing their child's distinctive backpack or favorite jacket. Prosopagnosia specifically impairs facial recognition, while the recognition of other objects or...
142
Depth Perception and Spatial Vision
599
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
599


