AggNet: Learning to Aggregate Faces for Group Membership Verification
This addresses group membership verification in face recognition for privacy-sensitive applications, but it is incremental as it builds on existing aggregation mechanisms.
The paper tackles the problem of verifying whether an individual is a member of a group without revealing their identity, and the proposed method achieves higher verification performance on multiple large-scale wild-face datasets compared to other baselines.
In some face recognition applications, we are interested to verify whether an individual is a member of a group, without revealing their identity. Some existing methods, propose a mechanism for quantizing precomputed face descriptors into discrete embeddings and aggregating them into one group representation. However, this mechanism is only optimized for a given closed set of individuals and needs to learn the group representations from scratch every time the groups are changed. In this paper, we propose a deep architecture that jointly learns face descriptors and the aggregation mechanism for better end-to-end performances. The system can be applied to new groups with individuals never seen before and the scheme easily manages new memberships or membership endings. We show through experiments on multiple large-scale wild-face datasets, that the proposed method leads to higher verification performance compared to other baselines.