Solving the Families In the Wild Kinship Verification Challenge by Program Synthesis
This work addresses kinship verification for applications like social media and forensics, but it is incremental as it builds on existing competition frameworks.
The paper tackled kinship verification by participating in the 2021 Recognizing Families in the Wild challenge, achieving top-3 results using an ensemble of human-written and Codex-generated models.
Kinship verification is the task of determining whether a parent-child, sibling, or grandparent-grandchild relationship exists between two people and is important in social media applications, forensic investigations, finding missing children, and reuniting families. We demonstrate high quality kinship verification by participating in the 2021 Recognizing Families in the Wild challenge which provides the largest publicly available dataset in the field. Our approach is among the top 3 winning entries in the competition. We ensemble models written by both human experts and a foundation model, OpenAI Codex, trained on text and code. We use Codex to generate model variants, and also demonstrate its ability to generate entire running programs for kinship verification tasks of specific relationships.