Kinship verification on families in the wild with marginalized denoising metric learning

Shuyang Wang, Joseph P. Robinson, Yun Fu

Abstract:

With our Families In the Wild (FIW) dataset, which consists of labels 1, 000 families in over 12, 000 family photos, we benchmarked the largest kinship verification experiment to date. FIW, with its quality data and labels for full family trees found worldwide, more accurately is
the true, global distribution of blood relatives with a total 378, 300 face pairs of 9 different relationship types. This gives support to tackle the problem with modern-day data-driven methods, which are imperative due to the complex nature of tasks involving visual kinship recognition– many hidden factors and less discrimination when considering face pairs of blood relatives. For this, we propose a denoising auto-encoder-based robust metric learning (DML) framework and its marginalized version (mDML) to explicitly preserve the intrinsic structure of
data and simultaneously endow the discriminative information into the learned features. Large-scale experiments show that our method outperforms other features and metric-based approaches on each of the 9 relationship types.