2021
DOI: 10.1016/j.tics.2021.06.006
|View full text |Cite
|
Sign up to set email alerts
|

Generative adversarial networks unlock new methods for cognitive science

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
11
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 18 publications
(11 citation statements)
references
References 82 publications
0
11
0
Order By: Relevance
“…However, such direct engineering of the generative features restricts the models of each stimulus category to the imagination of human engineers. A promising alternative uses generative adversarial networks (GANs) [68] which can produce arguably more realistic images. However, although such indirect engineering could expand generative parameters beyond human imagination, GANs are more difficult to control and therefore so far cannot deliver controlled 3D models of stimulus categories as computer graphics does (but note progress on structuring latent spaces [69][70][71]).…”
Section: Trends Trends In In Cognitivementioning
confidence: 99%
“…However, such direct engineering of the generative features restricts the models of each stimulus category to the imagination of human engineers. A promising alternative uses generative adversarial networks (GANs) [68] which can produce arguably more realistic images. However, although such indirect engineering could expand generative parameters beyond human imagination, GANs are more difficult to control and therefore so far cannot deliver controlled 3D models of stimulus categories as computer graphics does (but note progress on structuring latent spaces [69][70][71]).…”
Section: Trends Trends In In Cognitivementioning
confidence: 99%
“…We investigated the trend of visual changes with each layer in our material (Fig 6) in which we used StyleGAN2. It shows the clear trends that the Coarse layers (1-4) correspond to the shape and posture, the Middle layers (5-8) correspond to physiognomy, and the Fine layers (9)(10)(11)(12)(13)(14)(15)(16)(17)(18) correspond to the color and texture of the face image. The fact that the Coarse and Middle layers have latent image features that bring about greater visual changes is consistent with the result that the RMSE in CP was lower in those layers.…”
Section: Discussionmentioning
confidence: 99%
“…Another study took advantage of GANs to continuously generate realistic images to examine the correlation between generated images and mental representations of visual experiences in terms of perceptual similarity and memory properties, and reported similarities with previous studies obtained with simpler visual stimuli 17 . In addition to improving the quality of the images generated by GANs, they presented a new experimental approach to cognitive science by generating continuously changing visual stimuli in a latent space composed of meaningful information structures 18 . Previous studies have revealed the relationship between human perception and cognitive response to the distance in stimulus space with continuously generated visual stimulus such as colors 19,20 .…”
Section: Introductionmentioning
confidence: 99%
“…Modern systems such as generative adversarial networks 65 and derivatives of the classical variational autoencoders (VAEs) such as vector-quantized VAEs 66 , 67 and nouveau VAEs, 68 which can be trained on large, naturalistic face databases, can synthesize tantalizingly realistic faces, complete with hair, opening up an interesting avenue for future research and applications. 69 , 70 , 71 , 72 , 73 However, understanding and disentangling their latent spaces remains challenging. 74 , 75 …”
Section: Discussionmentioning
confidence: 99%