2019
DOI: 10.1167/19.7.1
|View full text |Cite
|
Sign up to set email alerts
|

Are you from North or South India? A hard face-classification task reveals systematic representational differences between humans and machines

Abstract: We make a rich variety of judgments on faces, but the underlying features are poorly understood. Here we describe a challenging geographical-origin classification problem that elucidates feature representations in both humans and machine algorithms. In Experiment 1 , we collected a diverse set of 1,647 faces from India labeled with their fine-grained geographical origin (North vs. South India), characterized the categorization performance of 129 human subjects on these faces, and compare… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
7
1

Relationship

2
6

Authors

Journals

citations
Cited by 10 publications
(5 citation statements)
references
References 47 publications
0
5
0
Order By: Relevance
“…The stimuli comprised 20 co-registered Indian faces (19 male, 1 female) from the IISc Indian Face Dataset 5 . All faces were grayscale, upright and front-facing.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…The stimuli comprised 20 co-registered Indian faces (19 male, 1 female) from the IISc Indian Face Dataset 5 . All faces were grayscale, upright and front-facing.…”
Section: Methodsmentioning
confidence: 99%
“…Convolutional or deep neural networks have revolutionized computer vision with their human-like accuracy on object-recognition tasks, and their object representations match coarsely with the brain 2 , 3 . Yet they are still outperformed by humans 4 , 5 and show systematic finer-scale deviations from human perception 6 – 9 . Even these differences are largely quantitative in that there are no explicit or emergent properties that are present in humans but absent in deep networks.…”
Section: Introductionmentioning
confidence: 98%
“…Does the face-identity-trained CNN not just match the overall performance of humans, but also use similar strategies to solve the identity matching task ( 32 , 33 )? To address this question, we performed an analysis of the errors being made by humans and CNNs and computed the trial-by-trial predictivity of the human behavioral choices by CNNs (see SI Appendix , Supplementary Note 3 for details).…”
Section: Resultsmentioning
confidence: 99%
“…The first consists of technical studies that focus on the applications and capabilities of facial processing. This covers issues such as classification of faces based on regional affiliations -North and South Indian (Katti and Arun, 2019) or North, East and South Indian (Sarin and Panda, 2020), identification of genetic disorders in children (Narayanan et al, 2019), and detection of emotions (Singh and Benedict, 2020). The second stream of work consists of research papers, reports and other critical perspectives on the use of facial processing, highlighting associated risks, harms, and modes of regulation (Bhandari, 2021;Joshi, 2020;Aneja and Chamuah, 2020;Kovacs, 2020;Parsheera, 2019;Marda, 2019a;Basu and Sonkar, 2019).…”
Section: Related Workmentioning
confidence: 99%