publication . Preprint . Other literature type . 2019

CNN explains tuning properties of anterior, but not middle, face-processing areas in macaque IT

Raman, Rajani; Hosoya, Haruo;
Open Access
  • Published: 03 Jul 2019
  • Publisher: Cold Spring Harbor Laboratory
Abstract
A number of recent computational studies have emphasized quantitative similarity between convolutional neural networks (CNNs) and the visual ventral stream up to the inferotemporal (IT) cortex in the primate. However, whether such similarity holds for the face-selective areas, a subsystem of IT, is not clear. To address this question, we extensively investigate whether CNNs show facial tuning properties previously reported by four experimental studies on different macaque face areas. More specifically, while simulating the four experiments on a variety of CNN models optimized for classification, we attempted to make a correspondence between the model layers and ...
16 references, page 1 of 2

Cox DD, Meier P, Oertelt N, DiCarlo JJ (2005) “Breaking” position-invariant object recognition. Nature neuroscience 8:1145-1147.

Deng J, Berg AC, Li K, Fei-Fei L (2010) What does classifying more than 10,000 image categories tell us? Computer Vision-ECCV 2010:71-84.

Downing PE, Chan AWY, Peelen MV, Dodds CM, Kanwisher N (2005) Domain Specificity in Visual Cortex. Cereb Cortex 16:1453-1461. [OpenAIRE]

Einhäuser W, Hipp J, Eggert J, Körner E, König P (2005) Learning viewpoint invariant object representations using a temporal coherence principle. Biological Cybernetics 93:79-90. [OpenAIRE]

Farzmahdi A, Rajaei K, Ghodrati M, Ebrahimpour R, Khaligh-Razavi S-M (2016) A specialized face-processing model inspired by the organization of monkey face patches explains several face-specific phenomena observed in humans. Sci Rep 6:25025. [OpenAIRE]

Nilsback M-E, Zisserman A (2008) Automated Flower Classification over a Large Number of Classes. Indian Conference of Computer Vision and Graphic Image Processing:722-729. [OpenAIRE]

Ohayon S, Freiwald WA, Tsao DY (2012) What Makes a Cell Face Selective? The Importance of Contrast. Neuron 74:567-581. [OpenAIRE]

Olshausen BA, Field DJ (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381:607-609. [OpenAIRE]

O'Toole AJ, Castillo CD, Parde CJ, Hill MQ, Chellappa R (2018) Face Space Representations in Deep Convolutional Neural Networks. Trends in cognitive Sciences 22:794-809.

Parkhi OM, Vedaldi A, Zisserman A (2015) Deep Face Recognition. British Machine Vision Conference:41.1-41.12.

Rajalingham R, Issa EB, Bashivan P, Kar K, Schmidt K, DiCarlo JJ (2018) Large-Scale, HighResolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks. The Journal of neuroscience 38:7255-7269. [OpenAIRE]

Rawat W, Wang Z (2017) Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review. Neural Computation 29:2352-2449.

Sato T, Uchida G, Lescroart MD, Kitazono J, Okada M, Tanifuji M (2013) Object representation in inferior temporal cortex is organized hierarchically in a mosaic-like structure. Journal of Neuroscience 33:16642-16656. [OpenAIRE]

Schwartz O, Simoncelli EP (2001) Natural signal statistics and sensory gain control. Nature neuroscience 4:819-825.

Tsao DY, Freiwald WA, Knutsen TA, Mandeville JB, Tootell RBH (2003) Faces and objects in macaque cerebral cortex. Nature neuroscience 6:989-995. [OpenAIRE]

16 references, page 1 of 2
Abstract
A number of recent computational studies have emphasized quantitative similarity between convolutional neural networks (CNNs) and the visual ventral stream up to the inferotemporal (IT) cortex in the primate. However, whether such similarity holds for the face-selective areas, a subsystem of IT, is not clear. To address this question, we extensively investigate whether CNNs show facial tuning properties previously reported by four experimental studies on different macaque face areas. More specifically, while simulating the four experiments on a variety of CNN models optimized for classification, we attempted to make a correspondence between the model layers and ...
16 references, page 1 of 2

Cox DD, Meier P, Oertelt N, DiCarlo JJ (2005) “Breaking” position-invariant object recognition. Nature neuroscience 8:1145-1147.

Deng J, Berg AC, Li K, Fei-Fei L (2010) What does classifying more than 10,000 image categories tell us? Computer Vision-ECCV 2010:71-84.

Downing PE, Chan AWY, Peelen MV, Dodds CM, Kanwisher N (2005) Domain Specificity in Visual Cortex. Cereb Cortex 16:1453-1461. [OpenAIRE]

Einhäuser W, Hipp J, Eggert J, Körner E, König P (2005) Learning viewpoint invariant object representations using a temporal coherence principle. Biological Cybernetics 93:79-90. [OpenAIRE]

Farzmahdi A, Rajaei K, Ghodrati M, Ebrahimpour R, Khaligh-Razavi S-M (2016) A specialized face-processing model inspired by the organization of monkey face patches explains several face-specific phenomena observed in humans. Sci Rep 6:25025. [OpenAIRE]

Nilsback M-E, Zisserman A (2008) Automated Flower Classification over a Large Number of Classes. Indian Conference of Computer Vision and Graphic Image Processing:722-729. [OpenAIRE]

Ohayon S, Freiwald WA, Tsao DY (2012) What Makes a Cell Face Selective? The Importance of Contrast. Neuron 74:567-581. [OpenAIRE]

Olshausen BA, Field DJ (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381:607-609. [OpenAIRE]

O'Toole AJ, Castillo CD, Parde CJ, Hill MQ, Chellappa R (2018) Face Space Representations in Deep Convolutional Neural Networks. Trends in cognitive Sciences 22:794-809.

Parkhi OM, Vedaldi A, Zisserman A (2015) Deep Face Recognition. British Machine Vision Conference:41.1-41.12.

Rajalingham R, Issa EB, Bashivan P, Kar K, Schmidt K, DiCarlo JJ (2018) Large-Scale, HighResolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks. The Journal of neuroscience 38:7255-7269. [OpenAIRE]

Rawat W, Wang Z (2017) Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review. Neural Computation 29:2352-2449.

Sato T, Uchida G, Lescroart MD, Kitazono J, Okada M, Tanifuji M (2013) Object representation in inferior temporal cortex is organized hierarchically in a mosaic-like structure. Journal of Neuroscience 33:16642-16656. [OpenAIRE]

Schwartz O, Simoncelli EP (2001) Natural signal statistics and sensory gain control. Nature neuroscience 4:819-825.

Tsao DY, Freiwald WA, Knutsen TA, Mandeville JB, Tootell RBH (2003) Faces and objects in macaque cerebral cortex. Nature neuroscience 6:989-995. [OpenAIRE]

16 references, page 1 of 2
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue