# Supervised Contrastive Learning and Feature Fusion for Improved Kinship Verification

arXiv: https://arxiv.org/abs/2302.09556 · HTML: https://mlsanity.com/paper/2302.09556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 19 Feb 2023.

## Builds on (most cited first, 10 of 10)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [Families in the Wild (FIW): Large-Scale Kinship Image Database and Benchmarks](https://mlsanity.com/paper/1604.02182/) (2016)
- [Deep Fusion Siamese Network for Automatic Kinship Verification](https://mlsanity.com/paper/2006.00143/) (2020)
- [KinshipGAN: Synthesizing of Kinship Faces From Family Photos by Regularizing a Deep Face Network](https://mlsanity.com/paper/1806.08600/) (2018)
- [Achieving Better Kinship Recognition Through Better Baseline](https://mlsanity.com/paper/2006.11739/) (2020)
- [Challenge report: Recognizing Families In the Wild Data Challenge](https://mlsanity.com/paper/2006.00154/) (2020)
- [A Multi-Task Comparator Framework for Kinship Verification](https://mlsanity.com/paper/2006.01615/) (2020)
- [A Unified Approach to Kinship Verification](https://mlsanity.com/paper/2009.05871/) (2020)

## Abstract (arXiv)

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.