[논문]Face detection in untrained deep neural networks

Baek, Seungdae; Song, Min; Jang, Jaeson; Kim, Gwangsu; Paik, Se-Bum

doi:10.1038/s41467-021-27606-9

[해외논문] Face detection in untrained deep neural networks 원문보기

Nature communications, v.12 no.1, 2021년, pp.7328 -

Baek, Seungdae (Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141 Republic of Korea) , Song, Min (Program of Brain and Cognitive Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141 Republic of Korea) , Jang, Jaeson (Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141 Republic of Korea) , Kim, Gwangsu (Department of Physics, Korea Advanced Institute of Science and Technology, Daejeon, 34141 Republic of Korea) , Paik, Se-Bum (Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141 Republic of Korea)

Abstract ▼ AI-Helper

Face-selective neurons are observed in the primate visual pathway and are considered as the basis of face detection in the brain. However, it has been debated as to whether this neuronal selectivity can arise innately or whether it requires training from visual experience. Here, using a hierarchical deep neural network model of the ventral visual stream, we suggest a mechanism in which face-selectivity arises in the complete absence of training. We found that units selective to faces emerge robustly in randomly initialized networks and that these units reproduce many characteristics observed in monkeys. This innate selectivity also enables the untrained network to perform face-detection tasks. Intriguingly, we observed that units selective to various non-face objects can also arise innately in untrained networks. Our results imply that the random feedforward connections in early, untrained deep neural networks may be sufficient for initializing primitive visual selectivity.Face-selective neurons are observed in the primate visual pathway and are considered as the basis of face detection in the brain. Here, using a hierarchical deep neural network model of the ventral visual stream, the authors suggest that face selectivity arises in the complete absence of training.

참고문헌 (102)

1. Desimone R Face-selective cells in the temporal cortex of monkeys J. Cogn. Neurosci. 1991 3 1 8 23964801

상세보기
2. Tsao DY Moeller S Freiwald WA Comparing face patch systems in macaques and humans Proc. Natl Acad. Sci. USA 2008 105 19514 19519 19033466

상세보기
3. Afraz A Boyden ES DiCarlo JJ Optogenetic and pharmacological suppression of spatial clusters of face neurons reveal their causal role in face gender discrimination Proc. Natl Acad. Sci. USA 2015 112 6730 6735 25953336

상세보기
4. Sadagopan S Zarco W Freiwald WA A causal relationship between face-patch activity and face-detection behavior Elife 2017 6 1 14
5. Tsao DY Freiwald WA Tootell RBH Livingstone MS A cortical region consisting entirely of face-selective cells Science 2006 311 670 674 16456083

상세보기
6. Livingstone MS Development of the macaque face-patch system Nat. Commun. 2017 8 14897 28361890

상세보기
7. Freiwald WA Tsao DY Functional compartmentalization and viewpoint generalization within the macaque face-processing system Science 2010 330 845 851 21051642

상세보기
8. Cohen Kadosh K Johnson MH Developing a cortex specialized for face perception Trends Cogn. Sci. 2007 11 367 369 17631408
9. Rhodes G Michie PT Hughes ME Byatt G The fusiform face area and occipital face area show sensitivity to spatial relations in faces Eur. J. Neurosci. 2009 30 721 733 19674084

상세보기
10. Allison T Puce A McCarthy G Social perception from visual cues: role of the STS region Trends Cogn. Sci. 2000 4 267 278 10859571
11. Parr LA Hecht E Barks SK Preuss TM Votaw JR Face processing in the chimpanzee brain Curr. Biol. 2009 19 50 53 19097899

상세보기
12. Kanwisher N McDermott J Chun MM The fusiform face area: a module in human extrastriate cortex specialized for face perception J. Neurosci. 1997 17 4302 4311 9151747

상세보기
13. Furey ML Dissociation of face-selective cortical responses by attention Proc. Natl Acad. Sci. USA 2006 103 1065 1070 16415158

상세보기
14. Kanwisher N Yovel G The fusiform face area: a cortical region specialized for the perception of faces Philos. Trans. R. Soc. B Biol. Sci. 2006 361 2109 2128
15. Tong F Nakayama K Moscovitch M Weinrib O Kanwisher N Response properites of the human fusiform face area Cogn. Neuropsychol. 2000 17 257 280 20945183
16. Barton JJS Press DZ Keenan JP O’Connor M Lesions of the fusiform face area impair perception of facial configuration in prosopagnosia Neurology 2002 58 71 78 11781408

상세보기
17. Aparicio PL Issa EB DiCarlo JJ Neurophysiological organization of the middle face patch in macaque inferior temporal cortex J. Neurosci. 2016 36 12729 12745 27810930

상세보기
18. Chang L Tsao DY The code for facial identity in the primate brain Cell 2017 169 1013 1028.e14 28575666

상세보기
19. Freiwald WA Tsao DY Livingstone MS A face feature space in the macaque temporal lobe Nat. Neurosci. 2009 12 1187 1196 19668199

상세보기
20. Andrews TJ Davies-Thompson J Kingstone A Young AW Internal and external features of the face are represented holistically in face-selective regions of visual cortex J. Neurosci. 2010 30 3544 3552 20203214

상세보기
21. Rosa-Salva O Regolin L Vallortigara G Faces are special for newly hatched chicks: Evidence for inborn domain-specific mechanisms underlying spontaneous preferences for face-like stimuli Dev. Sci. 2010 13 565 577 20590721
22. Rosa Salva O Farroni T Regolin L Vallortigara G Johnson MH The evolution of social orienting: evidence from chicks (gallus gallus) and human newborns PLoS ONE 2011 6 e18802 21533093

상세보기
23. Versace E Damini S Stancher G Early preference for face-like stimuli in solitary species as revealed by tortoise hatchlings Proc. Natl Acad. Sci. USA 2020 117 24047 24049 32929003

상세보기
24. McGugin RW Gatenby JC Gore JC Gauthier I High-resolution imaging of expertise reveals reliable object selectivity in the fusiform face area related to perceptual performance Proc. Natl Acad. Sci. USA 2012 109 17063 17068 23027970

상세보기
25. Ponce CR Evolving images for visual neurons using a deep generative network reveals coding principles and neuronal preferences Cell 2019 177 999 1009.e10 31051108

상세보기
26. Arcaro MJ Schade PF Vincent JL Ponce CR Livingstone MS Seeing faces is necessary for face-domain formation Nat. Neurosci. 2017 20 1404 1412 28869581
27. Buiatti M Cortical route for facelike pattern processing in human newborns Proc. Natl Acad. Sci. USA 2019 116 4625 4630 30755519

상세보기
28. van den Hurk J Van Baelen M Op de Beeck HP Development of visual category selectivity in ventral visual cortex does not require visual experience Proc. Natl Acad. Sci. USA 2017 114 E4501 E4510 28507127

상세보기
29. Murty NAR Visual experience is not necessary for the development of face-selectivity in the lateral fusiform gyrus Proc. Natl Acad. Sci. USA 2020 117 23011 23020 32839334

상세보기
30. Ullman S Harari D Dorfman N From simple innate biases to complex visual concepts Proc. Natl Acad. Sci. USA 2012 109 18215 18220 23012418

상세보기
31. Deen B Organization of high-level visual cortex in human infants Nat. Commun. 2017 8 13995 28072399

상세보기
32. Johnson MH Dziurawiec S Ellis H Morton J Newborns’ preferential tracking of face-like stimuli and its subsequent decline Cognition 1991 40 1 19 1786670

상세보기
33. Sugita Y Face perception in monkeys reared with no exposure to faces Proc. Natl Acad. Sci. USA 2008 105 394 398 18172214

상세보기
34. Kenney MD Mason WA Hill SD Effects of age, objects, and visual experience on affective responses of rhesus monkeys to strangers Dev. Psychol. 1979 15 176

상세보기
35. Darwin, C. The Expression of Emotions in Animals and Man . London: Murray 11 , 1872 (1872).
36. Moscovitch M Winocur G Behrmann M What is special about face recognition? Nineteen experiments on a person with visual object agnosia and dyslexia but normal face recognition J. Cogn. Neurosci. 1997 9 555 604 23965118

상세보기
37. Yin RK Looking at upside-down faces J. Exp. Psychol. 1969 81 141

상세보기
38. Nelson CA The development and neural bases of face recognition Infant Child Dev. Int. J. Res. Pract. 2001 10 3 18
39. Kanwisher N Tong F Nakayama K The effect of face inversion on the human fusiform face area Cognition 1998 68 1 11 9775516
40. Kanwisher N Domain specificity in face perception Nat. Neurosci. 2000 3 759 763 10903567

상세보기
41. Tsao DY Livingstone MS Mechanisms of face perception Annu. Rev. Neurosci. 2008 31 411 437 18558862

상세보기
42. Rhodes G Byatt G Michie PT Puce A Is the fusiform face area specialized for faces, individuation, or expert individuation? J. Cogn. Neurosci. 2004 16 189 203 15068591

상세보기
43. Tarr MJ Gauthier I FFA: a flexible fusiform area for subordinate-level visual processing automatized by expertise Nat. Neurosci. 2000 3 764 769 10903568

상세보기
44. Gauthier I Skudlarski P Gore JC Anderson AW Expertise for cars and birds recruits brain areas involved in face recognition Nat. Neurosci. 2000 3 191 197 10649576

상세보기
45. Krizhevsky A Sutskever I Hinton GE Imagenet classification with deep convolutional neural networks Adv. Neural Inf. Process. Syst. 2012 25 1097 1105
46. Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In 3rd International Conferencing on Learning and Representation, ICLR 2015—Conference Track Proceedings , 1–14 (2015).
47. Yamins DLK Performance-optimized hierarchical models predict neural responses in higher visual cortex Proc. Natl Acad. Sci. USA 2014 111 8619 8624 24812127

상세보기
48. Cadieu CF Deep neural networks rival the representation of primate IT cortex for core visual object recognition PLoS Comput. Biol. 2014 10 e1003963 25521294

상세보기
49. Yamins DLK DiCarlo JJ Using goal-driven deep learning models to understand sensory cortex Nat. Neurosci. 2016 19 356 365 26906502

상세보기
50. Cichy, R. M. et al. The Algonauts Project: A Platform for Communication between the Sciences of Biological and Artificial Intelligence. In Proc. 2019 Conference on Cognitive Computational Neuroscience 2 (Cognitive Computational Neuroscience, 2019).
51. Grossman S Convergent evolution of face spaces across human face-selective neuronal groups and deep convolutional networks Nat. Commun. 2019 10 4934 31666525

상세보기
52. Bashivan P Kar K DiCarlo JJ Neural population control via deep image synthesis Science 2019 364 eaav9436 31048462

상세보기
53. Jarrett, K., Kavukcuoglu, K., Ranzato, M. A. & LeCun, Y. What is the best multi-stage architecture for object recognition? In Proc. 2009 IEEE 12th International Conference on Computer Vision , 2146–2153 (IEEE, 2009).
54. Pinto N Doukhan D DiCarlo JJ Cox DD A high-throughput screening approach to discovering good forms of biologically inspired visual representation PLoS Comput. Biol. 2009 5 e1000579 19956750

상세보기
55. Frankle, J., Dziugaite, G. K., Roy, D. M. & Carbin, M. Stabilizing the Lottery Ticket Hypothesis. arXiv :1903.01611v3, Preprint at https://arxiv.org/abs/1903.01611 (2019).
56. Ramanujan, V., Wortsman, M., Kembhavi, A., Farhadi, A. & Rastegari, M. What’s Hidden in a Randomly Weighted Neural Network? In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition , 11893–11902 (2020).
57. Ulyanov D Vedaldi A Lempitsky V Deep image prior Int. J. Comput. Vis. 2020 128 1867 1888

상세보기
58. LeCun, Y., Bottou, L., Orr, G. & Muller, K.-R. Efficient backprop. Neural Networks Tricks Trade (Springer, New York, 1998).
59. Stigliani A Weiner KS Grill-Spector K Temporal processing capacity in high-level visual cortex is domain specific J. Neurosci. 2015 35 12412 12424 26354910

상세보기
60. Duyck M Color tuning of face-selective neurons in macaque inferior temporal cortex eNeuro 2021 8 1 16
61. Long B Yu CP Konkle T Mid-level visual features underlie the high-level categorical organization of the ventral stream Proc. Natl Acad. Sci. USA 2018 115 E9015 E9024 30171168

상세보기
62. Cao, Q., Shen, L., Xie, W., Parkhi, O. M. & Zisserman, A. VGGFace2: A dataset for recognising faces across pose and age. Proc.—13th IEEE Int. Conf. Autom. Face Gesture Recognition, FG 2018 , 67–74 (2018).
63. Bonin V Histed MH Yurgenson S Clay Reid R Local diversity and fine-scale organization of receptive fields in mouse visual cortex J. Neurosci. 2011 31 18506 18521 22171051

상세보기
64. Dosovitskiy A Brox T Generating images with perceptual similarity metrics based on deep networks Adv. Neural Inf. Process. Syst. 2016 29 658 666
65. Russakovsky O Imagenet large scale visual recognition challenge Int. J. Comput. Vis. 2015 115 211 252

상세보기
66. LeCun, Y., Fu Jie Huang & Bottou, L. Learning methods for generic object recognition with invariance to pose and lighting. In Proc. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004 . 2 , 97–104 (IEEE, 2004).
67. Kavukcuoglu, K. et al. Learning convolutional feature hierarchies for visual recognition. Adv. Neural Inf. Process. Syst. 23 24th Annu. Conf. Neural Inf. Process. Syst. 2010, NIPS 2010 1–9 (2010).
68. LeCun, Y. Learning invariant feature hierarchies. In European Conference on Computer Vision , 496–505 (Springer, 2012).
69. Chidester, B., Do, M. N. & Ma, J. Rotation Equivariance and Invariance in Convolutional Neural Networks. arXiv :1805.12301v1, Preprint at https://arxiv.org/abs/1805.12301 (2018)
70. Srivastava, M. & Grill-Spector, K. The Effect of Learning Strategy versus Inherent Architecture Properties on the Ability of Convolutional Neural Networks to Develop Transformation Invariance. arXiv :1810.13128v1, Preprint at https://arxiv.org/abs/1810.13128 (2018).
71. Zoccolan D Kouh M Poggio T DiCarlo JJ Trade-off between object selectivity and tolerance in monkey inferotemporal cortex J. Neurosci. 2007 27 12292 12307 17989294

상세보기
72. Perrett DI Visual cells in the temporal cortex sensitive to face view and gaze direction Proc. R. Soc. Lond. Biol. Sci. 1985 223 293 317 2858100
73. Paik SB Ringach DL Retinal origin of orientation maps in visual cortex Nat. Neurosci. 2011 14 919 925 21623365

상세보기
74. Jang J Paik SB Interlayer repulsion of retinal ganglion cell mosaics regulates spatial organization of functional maps in the visual cortex J. Neurosci. 2017 37 12141 12152 29114075

상세보기
75. Jang J Song M Paik S-B Retino-cortical mapping ratio predicts columnar and salt-and-pepper organization in mammalian visual cortex Cell Rep. 2020 30 3270 3279.e3 32160536

상세보기
76. Song M Jang J Kim G Paik SB Projection of orthogonal tiling from the retina to the visual cortex Cell Rep. 2021 34 108581 33406438

상세보기
77. Haxby JV Distributed and overlapping representations of faces and objects in ventral temporal cortex Science 2001 293 2425 2430 11577229

상세보기
78. Wold S Esbensen K Geladi P Principal component analysis Chemom. Intell. Lab. Syst. 1987 2 37 52

상세보기
79. Kaufman, L. & Rousseeuw, P. J. Finding Groups in Data: an Introduction to Cluster Analysis . 344 (John Wiley & Sons, 2009).
80. Sailamul P Jang J Paik SB Synaptic convergence regulates synchronization-dependent spike transfer in feedforward neural networks J. Comput. Neurosci. 2017 43 189 202 28895002

상세보기
81. Socher, R. et al. Zero-Shot Learning Through Cross-Modal Transfer. In 1st International Conference on Learning Representation ICLR 2013—Working Track Proceedings, 1–7 (2013).
82. Saxe, A. M. et al. On random weights and unsupervised feature learning. In Icml (2011).
83. Verstraeten D Schrauwen B D’Haene M Stroobandt D An experimental unification of reservoir computing methods Neural Netw. 2007 20 391 403 17517492

상세보기
84. Bellec G A solution to the learning dilemma for recurrent networks of spiking neurons Nat. Commun. 2020 11 1 15 31911652
85. Weidel P Duarte R Morrison A Unsupervised learning and clustered connectivity enhance reinforcement learning in spiking neural networks Front. Comput. Neurosci. 2021 15 1 17
86. Tetzlaff C Kolodziejski C Timme M Tsodyks M Wörgötter F Synaptic scaling enables dynamically distinct short- and long-term memory formation PLoS Comput. Biol. 2013 9 1 12
87. Zhang B Delayed maturation of receptive field center/surround mechanisms in V2 Proc. Natl Acad. Sci. USA 2005 102 5862 5867 15824308

상세보기
88. Baldwin MKL Kaskan PM Zhang B Chino YM Kaas JH Cortical and subcortical connections of V1 and V2 in early postnatal macaque monkeys J. Comp. Neurol. 2012 520 544 569 21800316

상세보기
89. Bourne JA Rosa MGP Hierarchical development of the primate visual cortex, as revealed by neurofilament immunoreactivity: early maturation of the middle temporal area (MT) Cereb. Cortex 2006 16 405 414 15944371

상세보기
90. Kiorpes L Movshon JA Neural limitations on visual development in primates Vis. Neurosci 2003 1 159 173
91. Srihasam K Mandeville JB Morocz IA Sullivan KJ Livingstone MS Behavioral and anatomical consequences of early versus late symbol training in macaques Neuron 2012 73 608 619 22325210

상세보기
92. Srihasam K Vincent JL Livingstone MS Novel domain formation reveals proto-architecture in inferotemporal cortex Nat. Neurosci. 2014 17 1776 1783 25362472

상세보기
93. Yan Y Zhaoping L Lia W Bottom-up saliency and top-down learning in the primary visual cortex of monkeys Proc. Natl Acad. Sci. USA 2018 115 10499 10504 30254154

상세보기
94. Epshtein B Lifshitz I Ullman S Image interpretation by a single bottom-up top-down cycle Proc. Natl Acad. Sci. USA 2008 105 14298 14303 18796607

상세보기
95. Arcaro MJ Livingstone MS A hierarchical, retinotopic proto-organization of the primate visual system at birth Elife 2017 6 1 24
96. Tavazoie SF Reid RC Diverse receptive fields in the lateral geniculate nucleus during thalamocortical development Nat. Neurosci. 2000 3 608 616 10816318

상세보기
97. Gourier, N., Hall, D. & Crowley, J. L. Estimating face orientation from robust detection of salient facial structures. FG Net Work. Vis. Obs. Deictic Gestures 17–25 (2004).
98. Handl J Knowles J Kell DB Computational cluster validation in post-genomic data analysis Bioinformatics 2005 21 3201 3212 15914541

상세보기
99. Kriegeskorte N Simmons WK Bellgowan PS Baker CI Circular analysis in systems neuroscience: The dangers of double dipping Nat. Neurosci. 2009 12 535 540 19396166

상세보기
100. Cureton EE Rank-biserial correlation Psychometrika 1956 21 287 290

상세보기
101. Cohen, J. Statistical Power for the Behavioural Sciences (Hilsdale, NY Lawrence Erlbaum, 1988).
102. Vermeesch P Multi-sample comparison of detrital age distributions Chem. Geol. 2013 341 140 146

상세보기

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증