# Families in the Wild (FIW): Large-Scale Kinship Image Database and Benchmarks

arXiv: https://arxiv.org/abs/1604.02182 · HTML: https://mlsanity.com/paper/1604.02182/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2016.

## Built on by (most cited first, 13 of 13)

- [CASIA-Face-Africa: A Large-scale African Face Image Database](https://mlsanity.com/paper/2105.03632/) (2021)
- [The 5th Recognizing Families in the Wild Data Challenge: Predicting Kinship from Faces](https://mlsanity.com/paper/2111.00598/) (2021)
- [Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings](https://mlsanity.com/paper/2310.17451/) (2023)
- [StyleDiT: A Unified Framework for Diverse Child and Partner Faces Synthesis with Style Latent Diffusion Transformer](https://mlsanity.com/paper/2412.10785/) (2024)
- [ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training](https://mlsanity.com/paper/2501.07078/) (2025)
- [Kinship Verification Based on Cross-Generation Feature Interaction Learning](https://mlsanity.com/paper/2109.02809/) (2021)
- [Confidence-Calibrated Face and Kinship Verification](https://mlsanity.com/paper/2210.13905/) (2022)
- [KFC: Kinship Verification with Fair Contrastive Loss and Multi-Task Learning](https://mlsanity.com/paper/2309.10641/) (2023)
- [Solving the Families In the Wild Kinship Verification Challenge by Program Synthesis](https://mlsanity.com/paper/2110.07020/) (2021)
- [Supervised Contrastive Learning and Feature Fusion for Improved Kinship Verification](https://mlsanity.com/paper/2302.09556/) (2023)
- [Age-Invariant Face Embedding using the Wasserstein Distance](https://mlsanity.com/paper/2305.02745/) (2023)
- [Kinship Verification through a Forest Neural Network](https://mlsanity.com/paper/2504.18910/) (2025)
- [S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models](https://mlsanity.com/paper/2604.18512/) (2026)

## Abstract (arXiv)

We present the largest kinship recognition dataset to date, Families in the Wild (FIW). Motivated by the lack of a single, unified dataset for kinship recognition, we aim to provide a dataset that captivates the interest of the research community. With only a small team, we were able to collect, organize, and label over 10,000 family photos of 1,000 families with our annotation tool designed to mark complex hierarchical relationships and local label information in a quick and efficient manner. We include several benchmarks for two image-based tasks, kinship verification and family recognition. For this, we incorporate several visual features and metric learning methods as baselines. Also, we demonstrate that a pre-trained Convolutional Neural Network (CNN) as an off-the-shelf feature extractor outperforms the other feature types. Then, results were further boosted by fine-tuning two deep CNNs on FIW data: (1) for kinship verification, a triplet loss function was learned on top of the network of pre-trained weights; (2) for family recognition, a family-specific softmax classifier was added to the network.