Generative models for visualizing idiosyncratic impressions

Todorov, Alexander; Uddenberg, Stefan; Albohn, Daniel N.

doi:10.1111/bjop.12622

Cited by 4 publications

(7 citation statements)

References 16 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we noted already the potential of AI in generating stimuli and modelling the relation between cues and impressions (O'Toole & Hu, 2023;Todorov et al, 2023) as well as raising critical considerations around ensuring diversity in AI.…”

Section: Advances In Methodsmentioning

confidence: 93%

“…We also echo their suggestion to increase the use of out-of-sample testing. Similarly, Todorov et al (2023) point out the advantages of being able to estimate the reliability of each participant's responses by taking more than one response to the same stimulus.…”

Section: Advances In Methodsmentioning

confidence: 99%

“…Training data may also represent traits differently; for example, trustworthiness judgements may be more important for controlled, neutral face photos taken in the lab, whereas attractiveness may be more important when photos are from social media and online dating profiles created by users themselves (Keles et al, 2021). As Todorov et al (2023) note, and highlighted in our initial review, impression ratings and even face image choices could also be influenced by the judges' stereotypes. We, therefore, emphasize that it is critical that AI models are representative of diverse populations for targets and judges and based on input from diverse research communities.…”

Section: Embracing Diversitymentioning

confidence: 99%

“…Aside from impressions due to the attributes of the target, Todorov et al (2023) remind us of the importance of understanding individual differences in perceivers' impressions. We agree with their suggestion that understanding these individual differences is 'one of the most important, most underappreciated and least developed areas of research on first impressions'.…”

Section: Beyond the Facementioning

confidence: 99%

“…Mondloch et al (2023) also agree with us that it is important now to move beyond studies that include only White faces and impressions derived from Western participants. They suggest that artificial intelligence techniques (AI) can be used to generate more diverse faces, as do O'Toole and Hu (2023) and Todorov et al (2023). While such approaches will be valuable, it remains the case that AI itself will still be constrained by its training data; an AI model that has never seen images of people from Aboriginal and Torres Strait Islander cultures would struggle to generate plausible faces representing these groups, a model that has only been trained on Black faces would be unlikely to create realistic White or Asian faces and so forth.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A first impression of the future

Sutherland

Young

2023

British J of Psychology

View full text Add to dashboard Cite

We offer a response to six commentaries on our target article ‘Understanding trait impressions from faces’. A broad consensus emerged with authors emphasizing the importance of increasing the diversity of faces and participants, integrating research on impressions beyond the face, and continuing to develop methods needed for data‐driven approaches. We propose future directions for the field based on these themes.

show abstract

Section: Advances In Methodsmentioning

confidence: 93%

Section: Advances In Methodsmentioning

confidence: 99%

Section: Embracing Diversitymentioning

confidence: 99%

Section: Beyond the Facementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A first impression of the future

Sutherland

Young

2023

British J of Psychology

View full text Add to dashboard Cite

show abstract

Generative neural networks for experimental manipulation: Examining dominance‐trustworthiness face impressions with data‐efficient models

Sobieszek,

Siemiątkowski,

Imbir

2024

British J of Psychology

View full text Add to dashboard Cite

An important development in the study of face impressions was the introduction of dominance and trustworthiness as the primary and potentially orthogonal traits judged from faces. We test competing predictions of recent accounts that address evidence against the independence of these judgements. To this end we develop a version of recent ‘deep models of face impressions’ better suited for data‐efficient experimental manipulation. In Study 1 (N = 128) we build impression models using 15 times less ratings per dimension than previously assumed necessary. In Study 2 (N = 234) we show how our method can precisely manipulate dominance and trustworthiness impressions of face photographs and observe how the effects' pattern of the cues of one trait on impressions of the other differs from previous accounts. We propose an altered account that stresses how a successful execution of the two judgements' functional roles requires impressions of trustworthiness and dominance to be based on cues of both traits. Finally we show our manipulation resulted in larger effect sizes using a broader array of features than previous methods. Our approach lets researchers manipulate face stimuli for various face perception studies and investigate new dimensions with minimal data collection.

show abstract

Facecraft: Race Reification in Psychological Research With Faces

Martinez

2023

Perspect Psychol Sci

View full text Add to dashboard Cite

Faces are socially important surfaces of the body on which various meanings are attached. The widespread physiognomic belief that faces inherently contain socially predictive value is why they make a generative stimulus for perception research. However, critical problems arise in studies that simultaneously investigate faces and race. Researchers studying race and racism inadvertently engage in various research practices that transform faces with specific phenotypes into straightforward representatives of their presumed race category, thereby taking race and its phenotypic associations for granted. I argue that research practices that map race categories onto faces using bioessentialist ideas of racial phenotypes constitute a form of racecraft ideology, the dubious reasoning of which presupposes the reality of race and mystifies the causal relation between race and racism. In considering how to study racism without reifying race in face studies, this article places these practices in context, describes how they reproduce racecraft ideology and impair theoretical inferences, and then suggests counterpractices for minimizing this problem.

show abstract

Generative models for visualizing idiosyncratic impressions

Cited by 4 publications

References 16 publications

A first impression of the future

A first impression of the future

Generative neural networks for experimental manipulation: Examining dominance‐trustworthiness face impressions with data‐efficient models

Facecraft: Race Reification in Psychological Research With Faces

Contact Info

Product

Resources

About