PT  - JOURNAL ARTICLE
AU  - Jozwik, Kamila M.
AU  - O’Keeffe, Jonathan
AU  - Storrs, Katherine R.
AU  - Kriegeskorte, Nikolaus
TI  - Face dissimilarity judgements are predicted by representational distance in deep neural networks and principal-component face space
AID  - 10.1101/2021.04.09.438859
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.04.09.438859
4099  - http://biorxiv.org/content/early/2021/04/10/2021.04.09.438859.short
4100  - http://biorxiv.org/content/early/2021/04/10/2021.04.09.438859.full
AB  - Despite the importance of face perception in human and computer vision, no quantitative model of perceived face dissimilarity exists. We designed an efficient behavioural task to collect dissimilarity and same/different identity judgements for 232 pairs of realistic faces that densely sampled geometric relationships in a face space derived from principal components of 3D shape and texture (Basel Face Model, BFM). In a comparison of 15 models, we found that representational distances in deep neural networks (DNNs) and Euclidean distances within BFM space predicted human judgements best. A face-trained DNN explained unique variance over simpler models and was statistically indistinguishable from the noise ceiling. Sigmoidal transformation of distances improved performance for all models. Identity judgements were better predicted by Euclidean than angular or radial distances in BFM space. DNNs provide the best available image-computable models of perceived face dissimilarity. The success of BFM space suggests that human face perception is attuned to the natural distribution of faces.Competing Interest StatementThe authors have declared no competing interest.