Achieving Better Kinship Recognition Through Better Baseline

TL;DR

This paper introduces a new baseline for kinship recognition using face verification techniques, leveraging recent face recognition advancements to improve accuracy in recognizing blood relations from face images.

Contribution

It presents a novel kinship recognition pipeline based on RetinaFace and ArcFace, achieving state-of-the-art results in recent kinship recognition challenges.

Findings

Achieved state-of-the-art performance on kinship recognition benchmarks.

Demonstrated the effectiveness of transfer learning from face verification to kinship recognition.

Established a strong baseline for future kinship recognition research.

Abstract

Recognizing blood relations using face images can be seen as an application of face recognition systems with additional restrictions. These restrictions proved to be difficult to deal with, however, recent advancements in face verification show that there is still much to gain using more data and novel ideas. As a result face recognition is a great source domain from which we can transfer the knowledge to get better performance in kinship recognition as a source domain. We present a new baseline for an automatic kinship recognition task and relatives search based on RetinaFace[1] for face registration and ArcFace[2] face verification model. With the approach described above as the foundation, we constructed a pipeline that achieved state-of-the-art performance on two tracks in the recent Recognizing Families In the Wild Data Challenge.