The face inversion effect through the lens of deep neural networks.
作者信息
Tousi Ehsan, Mur Marieke
机构信息
Department of Psychology, Western University, 1151 Richmond Street , London, Ontario N6A 3K7, Canada.
Neuroscience Graduate Program, Western University, 1151 Richmond Street , London, Ontario N6A 3K7, Canada.
出版信息
Proc Biol Sci. 2024 Aug;291(2028):20241342. doi: 10.1098/rspb.2024.1342. Epub 2024 Aug 14.
Abstract
摘要
相似文献
1
The face inversion effect through the lens of deep neural networks.从深度神经网络视角看面部倒置效应。
Proc Biol Sci. 2024 Aug;291(2028):20241342. doi: 10.1098/rspb.2024.1342. Epub 2024 Aug 14.
2
Human-like face pareidolia emerges in deep neural networks optimized for face and object recognition.类人脸空想性错觉出现在针对面部和物体识别进行优化的深度神经网络中。
PLoS Comput Biol. 2025 Jan 27;21(1):e1012751. doi: 10.1371/journal.pcbi.1012751. eCollection 2025 Jan.
3
4
Face Recognition Depends on Specialized Mechanisms Tuned to View-Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition.人脸识别依赖于专门的机制，这些机制针对的是不变的面部特征：来自专门针对人脸或物体识别进行优化的深度神经网络的见解。
Cogn Sci. 2021 Sep;45(9):e13031. doi: 10.1111/cogs.13031.
5
Enhanced AlexNet with Gabor and Local Binary Pattern Features for Improved Facial Emotion Recognition.用于改进面部表情识别的具有Gabor和局部二值模式特征的增强型AlexNet
Sensors (Basel). 2025 Jun 19;25(12):3832. doi: 10.3390/s25123832.
6
Conceptual Knowledge Shapes the Neural Representations of Learned Faces in Non-Visual Regions of the Brain.概念性知识塑造大脑非视觉区域中习得面孔的神经表征。
J Neurosci. 2025 Jul 30;45(31):e0122252025. doi: 10.1523/JNEUROSCI.0122-25.2025.
7
Face Space Representations in Deep Convolutional Neural Networks.深度卷积神经网络中的人脸空间表示。
Trends Cogn Sci. 2018 Sep;22(9):794-809. doi: 10.1016/j.tics.2018.06.006. Epub 2018 Aug 7.
8
Intracranial Electroencephalography and Deep Neural Networks Reveal Shared Substrates for Representations of Face Identity and Expressions.颅内脑电图和深度神经网络揭示了面部身份和表情表示的共享基础。
J Neurosci. 2023 Jun 7;43(23):4291-4303. doi: 10.1523/JNEUROSCI.1277-22.2023. Epub 2023 May 4.
9
Effect of altitude on the spatiotemporal signal characteristics of inversion face recognition.海拔高度对倒向人脸识别时空信号特征的影响。
Sci Rep. 2025 Jul 15;15(1):25462. doi: 10.1038/s41598-025-10442-y.
10
Facial Expressions Recognition for Human-Robot Interaction Using Deep Convolutional Neural Networks with Rectified Adam Optimizer.基于修正 Adam 优化器的深度卷积神经网络的人机交互中的面部表情识别。
Sensors (Basel). 2020 Apr 23;20(8):2393. doi: 10.3390/s20082393.
本文引用的文献
1
The neural code for "face cells" is not face-specific.“面孔细胞”的神经编码并非特异性面孔。
Sci Adv. 2023 Sep;9(35):eadg1736. doi: 10.1126/sciadv.adg1736. Epub 2023 Aug 30.
2
Behavioral signatures of face perception emerge in deep neural networks optimized for face recognition.深度神经网络在优化人脸识别时会出现面部感知的行为特征。
Proc Natl Acad Sci U S A. 2023 Aug 8;120(32):e2220642120. doi: 10.1073/pnas.2220642120. Epub 2023 Jul 31.
3
Deep learning models challenge the prevailing assumption that face-like effects for objects of expertise support domain-general mechanisms.深度学习模型挑战了这样一种主流假设，即对于专业领域物体的类似面孔的效应支持领域普遍的机制。
Proc Biol Sci. 2023 May 10;290(1998):20230093. doi: 10.1098/rspb.2023.0093.
4
CNNs reveal the computational implausibility of the expertise hypothesis.卷积神经网络揭示了专业技能假设在计算上的不合理性。
iScience. 2023 Jan 14;26(2):105976. doi: 10.1016/j.isci.2023.105976. eCollection 2023 Feb 17.
5
Brain-like functional specialization emerges spontaneously in deep neural networks.类脑功能特化在深度神经网络中自发出现。
Sci Adv. 2022 Mar 18;8(11):eabl8913. doi: 10.1126/sciadv.abl8913. Epub 2022 Mar 16.
6
A self-supervised domain-general learning framework for human ventral stream representation.一种用于人类腹侧流表示的自监督领域泛化学习框架。
Nat Commun. 2022 Jan 25;13(1):491. doi: 10.1038/s41467-022-28091-4.
7
A connectivity-constrained computational account of topographic organization in primate high-level visual cortex.灵长类高级视觉皮层拓扑组织的连接约束计算解释。
Proc Natl Acad Sci U S A. 2022 Jan 18;119(3). doi: 10.1073/pnas.2112566119.
8
A map of object space in primate inferotemporal cortex.灵长类动物下颞叶皮层的客体空间图谱。
Nature. 2020 Jul;583(7814):103-108. doi: 10.1038/s41586-020-2350-5. Epub 2020 Jun 3.
9
Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing.深度神经网络：一种用于模拟生物视觉和大脑信息处理的新框架。
Annu Rev Vis Sci. 2015 Nov 24;1:417-446. doi: 10.1146/annurev-vision-082114-035447.
10
The fusiform face area subserves face perception, not generic within-category identification.梭状回面孔区负责面孔感知，而非一般的类别内识别。
Nat Neurosci. 2004 May;7(5):555-62. doi: 10.1038/nn1224. Epub 2004 Apr 11.
Zotero 插件