"To address these limitations, we perform a megastudy—a survey-based study that reports the predictability of numerous personal attributes (349 binary variables) from 2646 distinct facial images of 969 individuals. Using deep learning, we find 82/349 personal attributes (23%) are predictable better than random from facial image pixels."
If you look at the findings neatly summarized in Fig. 2, the predictable ones are as one might expect (race, gender, age, etc.), and the rest is just plain pseudo-science, even though the authors seem to interpret AUC ~= 0.6 as "predicatable" instead of plain noise. Nature's reviewers should take a hint.
2 comments
[ 2392 ms ] story [ 1180 ms ] thread"To address these limitations, we perform a megastudy—a survey-based study that reports the predictability of numerous personal attributes (349 binary variables) from 2646 distinct facial images of 969 individuals. Using deep learning, we find 82/349 personal attributes (23%) are predictable better than random from facial image pixels."
If you look at the findings neatly summarized in Fig. 2, the predictable ones are as one might expect (race, gender, age, etc.), and the rest is just plain pseudo-science, even though the authors seem to interpret AUC ~= 0.6 as "predicatable" instead of plain noise. Nature's reviewers should take a hint.