Supervised Contrastive Learning and Feature Fusion for Improved Kinship Verification
This addresses kinship verification for applications in forensic science, social media, and demographic studies, but appears incremental as it builds on existing deep learning approaches.
The paper tackled facial kinship verification by proposing a method using supervised contrastive learning to maximize similarity between related individuals and minimize it between unrelated ones, achieving 81.1% accuracy on the Families in the Wild dataset.
Facial Kinship Verification is the task of determining the degree of familial relationship between two facial images. It has recently gained a lot of interest in various applications spanning forensic science, social media, and demographic studies. In the past decade, deep learning-based approaches have emerged as a promising solution to this problem, achieving state-of-the-art performance. In this paper, we propose a novel method for solving kinship verification by using supervised contrastive learning, which trains the model to maximize the similarity between related individuals and minimize it between unrelated individuals. Our experiments show state-of-the-art results and achieve 81.1% accuracy in the Families in the Wild (FIW) dataset.