# AggNet: Learning to Aggregate Faces for Group Membership Verification

arXiv: https://arxiv.org/abs/2206.08683 · HTML: https://mlsanity.com/paper/2206.08683/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 17 Jun 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances](https://mlsanity.com/paper/2009.13290/) (2020)
- [GhostVLAD for set-based face recognition](https://mlsanity.com/paper/1810.09951/) (2018)
- [Bags of Local Convolutional Features for Scalable Instance Search](https://mlsanity.com/paper/1604.04653/) (2016)
- [Compact Deep Aggregation for Set Retrieval](https://mlsanity.com/paper/2003.11794/) (2020)
- [Aggregation and Embedding for Group Membership Verification](https://mlsanity.com/paper/1812.03943/) (2018)
- [Privacy Preserving Group Membership Verification and Identification](https://mlsanity.com/paper/1904.10327/) (2019)

## Abstract (arXiv)

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.