Use of superordinate labels yields more robust and human-like visual representations in convolutional neural networks

被引:3
作者
Ahn, Seoyoung [1 ]
Zelinsky, Gregory J. [1 ,2 ]
Lupyan, Gary [3 ]
机构
[1] SUNY Stony Brook, Dept Psychol, Stony Brook, NY 11794 USA
[2] SUNY Stony Brook, Dept Comp Sci, Stony Brook, NY 11794 USA
[3] Univ Wisconsin, Dept Psychol, 1202 W Johnson St, Madison, WI 53706 USA
来源
JOURNAL OF VISION | 2021年 / 21卷 / 13期
关键词
BASIC-LEVEL; CONCEPTUAL KNOWLEDGE; RECOGNITION; LANGUAGE; OBJECTS; CLASSIFICATION; CATEGORIZATION; INVARIANCE; RESPONSES; CONTRAST;
D O I
10.1167/jov.21.13.13
中图分类号
R77 [眼科学];
学科分类号
100212 ;
摘要
引用
收藏
页数:19
相关论文
共 78 条
  • [1] Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
    Akhtar, Naveed
    Mian, Ajmal
    [J]. IEEE ACCESS, 2018, 6 : 14410 - 14430
  • [2] Labels Direct Infants' Attention to Commonalities during Novel Category Learning
    Althaus, Nadja
    Mareschal, Denis
    [J]. PLOS ONE, 2014, 9 (07):
  • [3] Preserving Semantic Relations for Zero-Shot Learning
    Annadani, Yashas
    Biswas, Soma
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 7603 - 7612
  • [4] [Anonymous], 2014, LME4 LINEAR MIXED EF
  • [5] [Anonymous], 1982, Visual perception
  • [6] Contrast sensitivity in human visual areas and its relationship to object recognition
    Avidan, G
    Harel, M
    Hendler, T
    Ben-Bashat, D
    Zohary, E
    Malach, R
    [J]. JOURNAL OF NEUROPHYSIOLOGY, 2002, 87 (06) : 3102 - 3116
  • [7] Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
    Ba, Jimmy Lei
    Swersky, Kevin
    Fidler, Sanja
    Salakhutdinov, Ruslan
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 4247 - 4255
  • [8] Mixed-effects modeling with crossed random effects for subjects and items
    Baayen, R. H.
    Davidson, D. J.
    Bates, D. M.
    [J]. JOURNAL OF MEMORY AND LANGUAGE, 2008, 59 (04) : 390 - 412
  • [9] Deep convolutional networks do not classify based on global object shape
    Baker, Nicholas
    Lu, Hongjing
    Erlikhman, Gennady
    Kellman, Philip J.
    [J]. PLOS COMPUTATIONAL BIOLOGY, 2018, 14 (12)
  • [10] Barbu A, 2019, ADV NEUR IN, V32