{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/families-in-the-wild-fiw-large-scale-kinship","title":"Families in the Wild (FIW): Large-Scale Kinship Image Database and Benchmarks","arxiv_id":"1604.02182","date":"2016-04-07","proceeding":null,"authors":["Joseph P. Robinson","Ming Shao","Yue Wu","Yun Fu"],"abstract":"We present the largest kinship recognition dataset to date, Families in the\nWild (FIW). Motivated by the lack of a single, unified dataset for kinship\nrecognition, we aim to provide a dataset that captivates the interest of the\nresearch community. With only a small team, we were able to collect, organize,\nand label over 10,000 family photos of 1,000 families with our annotation tool\ndesigned to mark complex hierarchical relationships and local label information\nin a quick and efficient manner. We include several benchmarks for two\nimage-based tasks, kinship verification and family recognition. For this, we\nincorporate several visual features and metric learning methods as baselines.\nAlso, we demonstrate that a pre-trained Convolutional Neural Network (CNN) as\nan off-the-shelf feature extractor outperforms the other feature types. Then,\nresults were further boosted by fine-tuning two deep CNNs on FIW data: (1) for\nkinship verification, a triplet loss function was learned on top of the network\nof pre-trained weights; (2) for family recognition, a family-specific softmax\nclassifier was added to the network.","url_abs":"http://arxiv.org/abs/1604.02182v2","url_pdf":"http://arxiv.org/pdf/1604.02182v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"kinship-verification","task_name":"Kinship Verification"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[{"slug":"fiw","name":"FIW","full_name":"Families In The Wild"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}