Implementation-Independent Representation for Deep Convolutional Neural Networks and Humans in Processing Faces

被引:7
|
作者
Song, Yiying [1 ]
Qu, Yukun [2 ]
Xu, Shan [1 ]
Liu, Jia [3 ,4 ]
机构
[1] Beijing Normal Univ, Fac Psychol, Beijing Key Lab Appl Expt Psychol, Beijing, Peoples R China
[2] Beijing Normal Univ, State Key Lab Cognit Neurosci & Learning, Beijing, Peoples R China
[3] Tsinghua Univ, Dept Psychol, Beijing, Peoples R China
[4] Tsinghua Univ, Tsinghua Lab Brain & Intelligence, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
deep convolutional neural network; face recognition; reverse correlation analysis; face representation; visual intelligence; OBJECT; INFORMATION;
D O I
10.3389/fncom.2020.601314
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Deep convolutional neural networks (DCNN) nowadays can match human performance in challenging complex tasks, but it remains unknown whether DCNNs achieve human-like performance through human-like processes. Here we applied a reverse-correlation method to make explicit representations of DCNNs and humans when performing face gender classification. We found that humans and a typical DCNN, VGG-Face, used similar critical information for this task, which mainly resided at low spatial frequencies. Importantly, the prior task experience, which the VGG-Face was pre-trained to process faces at the subordinate level (i.e., identification) as humans do, seemed necessary for such representational similarity, because AlexNet, a DCNN pre-trained to process objects at the basic level (i.e., categorization), succeeded in gender classification but relied on a completely different representation. In sum, although DCNNs and humans rely on different sets of hardware to process faces, they can use a similar and implementation-independent representation to achieve the same computation goal.
引用
收藏
页数:9
相关论文
共 50 条
  • [21] Distinct patterns of neural response to faces from different races in humans and deep networks
    Wang, Ao
    Sliwinska, Magdalena W.
    Watson, David M.
    Smith, Sam
    Andrews, Timothy J.
    SOCIAL COGNITIVE AND AFFECTIVE NEUROSCIENCE, 2023, 18 (01)
  • [22] The Representation of Speech and Its Processing in the Human Brain and Deep Neural Networks
    Scharenborg, Odette
    SPEECH AND COMPUTER, SPECOM 2019, 2019, 11658 : 1 - 8
  • [23] Numerosity representation in a deep convolutional neural network
    Zhou, Cihua
    Xu, Wei
    Liu, Yujie
    Xue, Zhichao
    Chen, Rui
    Zhou, Ke
    Liu, Jia
    JOURNAL OF PACIFIC RIM PSYCHOLOGY, 2021, 15
  • [24] Crowding in humans is unlike that in convolutional neural networks
    Lonnqvist, Ben
    Clarke, Alasdair D. F.
    Chakravarthi, Ramakrishna
    NEURAL NETWORKS, 2020, 126 : 262 - 274
  • [25] Deepfakes Classification of Faces Using Convolutional Neural Networks
    Sharma, Jatin
    Sharma, Sahil
    Kumar, Vijay
    Hussein, Hany S.
    Alshazly, Hammam
    TRAITEMENT DU SIGNAL, 2022, 39 (03) : 1027 - 1037
  • [26] PROCESSING CONVOLUTIONAL NEURAL NETWORKS ON CACHE
    Vieira, Joao
    Roma, Nuno
    Falcao, Gabriel
    Tomas, Pedro
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 1658 - 1662
  • [27] Suitability of Features of Deep Convolutional Neural Networks for Modeling Somatosensory Information Processing
    Kursun, Olcay
    Favorov, Oleg, V
    PATTERN RECOGNITION AND TRACKING XXX, 2019, 10995
  • [28] Deep Anchored Convolutional Neural Networks
    Huang, Jiahui
    Dwivedi, Kshitij
    Roig, Gemma
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 639 - 647
  • [29] DEEP CONVOLUTIONAL NEURAL NETWORKS FOR LVCSR
    Sainath, Tara N.
    Mohamed, Abdel-rahman
    Kingsbury, Brian
    Ramabhadran, Bhuvana
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 8614 - 8618
  • [30] Deep Unitary Convolutional Neural Networks
    Chang, Hao-Yuan
    Wang, Kang L.
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2021, PT II, 2021, 12892 : 170 - 181