2018
DOI: 10.31234/osf.io/e5hgx
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

The Invariance of Recognition to the Stretching of Faces is Not Explained by Familiarity or Warping to an Average Face

Abstract: Stretching (or compressing) a face by a factor of two has no effect on its recognition as assessed by the speed and accuracy of judging whether the face is that of a celebrity (Hole, 2002). This invariance has stood as a challenge to all contemporary accounts of the relation between neurocomputational measures of face similarity and face recognition. We extend the documentation of strong invariance over compression to a factor of four and show that the deformation so produced is sufficiently great that the res… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 15 publications
(3 citation statements)
references
References 32 publications
0
3
0
Order By: Relevance
“…Humans can identify objects that are highly distorted or highly degraded. For instance, we can readily identify images of faces that are stretched by a factor of four (Hacker & Biederman, 2018), when images are partly occluded or presented in novel poses (Biederman, 1987), and when various sorts of visual noise are added to the image (Geirhos et al, 2021). By contrast, CNNs are much worse at generalizing under these conditions (Alcorn et al, 2019;Geirhos et al, 2018Geirhos et al, , 2021Wang et al, 2018;Zhu, Tang, Park, Park, & Yuille, 2019).…”
Section: Dnns Are Poor At Identifying Degraded and Deformed Imagesmentioning
confidence: 99%
“…Humans can identify objects that are highly distorted or highly degraded. For instance, we can readily identify images of faces that are stretched by a factor of four (Hacker & Biederman, 2018), when images are partly occluded or presented in novel poses (Biederman, 1987), and when various sorts of visual noise are added to the image (Geirhos et al, 2021). By contrast, CNNs are much worse at generalizing under these conditions (Alcorn et al, 2019;Geirhos et al, 2018Geirhos et al, , 2021Wang et al, 2018;Zhu, Tang, Park, Park, & Yuille, 2019).…”
Section: Dnns Are Poor At Identifying Degraded and Deformed Imagesmentioning
confidence: 99%
“…4.1.7 DNNs are poor at identifying degraded and deformed images: Humans can identify objects that are highly distorted or highly degraded. For instance, we can readily identify images of faces that are stretched by a factor of four (Hacker & Biederman, 2018), when images are partly occluded or presented in novel poses (Biederman, 1987), and when various sorts of visual noise are added to the image (Geirhos et al, 2021). By contrast, CNNs are much worse at generalizing under these conditions (Alcorn et al, 2019;Geirhos et al, 2018Geirhos et al, , 2021Wang et al, 2018;Zhu, Tang, Park, Park, & Yuille, 2019).…”
Section: Dnns Fail To Show Uncrowdingmentioning
confidence: 99%
“…DNNs are poor at identifying degraded and deformed images Humans can identify objects that are highly distorted or highly degraded. For instance, we can readily identify images of faces that are stretched by a factor of four (Hacker & Biederman, 2018), when images are partly occluded or presented in novel poses , and when various sorts of visual noise are added to the image . By contrast, CNNs are much worse at generalizing under these conditions (Alcorn et al, 2019;Geirhos et al, 2018Wang et al, Figure 9.…”
Section: Dnns Fail To Show Uncrowdingmentioning
confidence: 99%