Kinship Identification through Joint Learning Using Kinship Verification Ensembles

TL;DR

This paper introduces a novel kinship identification method using joint learning of verification ensembles and classification, addressing dataset bias and improving accuracy over existing approaches.

Contribution

It presents a new kinship identification approach with joint training and dataset rebalancing, enhancing performance and realism in kinship verification tasks.

Findings

Improved kinship identification accuracy with joint learning.

Dataset rebalancing leads to more realistic training and better generalization.

Enhanced kinship verification performance when trained on balanced data.

Abstract

Kinship verification is a well-explored task: identifying whether or not two persons are kin. In contrast, kinship identification has been largely ignored so far. Kinship identification aims to further identify the particular type of kinship. An extension to kinship verification run short to properly obtain identification, because existing verification networks are individually trained on specific kinships and do not consider the context between different kinship types. Also, existing kinship verification datasets have biased positive-negative distributions which are different than real-world distributions. To this end, we propose a novel kinship identification approach based on joint training of kinship verification ensembles and classification modules. We propose to rebalance the training dataset to become more realistic. Large scale experiments demonstrate the appealing performance on kinship identification. The experiments further show significant performance improvement of kinship verification when trained on the same dataset with more realistic distributions.