# Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition

arXiv: https://arxiv.org/abs/1809.01407 · HTML: https://mlsanity.com/paper/1809.01407/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2018.

## Built on by (most cited first, 20 of 20)

- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodes](https://mlsanity.com/paper/2103.13225/) (2021)
- [Learning Hierarchical Graph Neural Networks for Image Clustering](https://mlsanity.com/paper/2107.01319/) (2021)
- [Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.12585/) (2021)
- [Panoramic Human Activity Recognition](https://mlsanity.com/paper/2203.03806/) (2022)
- [QClusformer: A Quantum Transformer-based Framework for Unsupervised Visual Clustering](https://mlsanity.com/paper/2405.19722/) (2024)
- [Quantum Visual Feature Encoding Revisited](https://mlsanity.com/paper/2405.19725/) (2024)
- [Self-supervised Social Relation Representation for Human Group Detection](https://mlsanity.com/paper/2203.03843/) (2022)
- [Learn to Cluster Faces via Pairwise Classification](https://mlsanity.com/paper/2205.13117/) (2022)
- [On Mitigating Hard Clusters for Face Clustering](https://mlsanity.com/paper/2207.11895/) (2022)
- [Learning to Cluster Faces via Transformer](https://mlsanity.com/paper/2104.11502/) (2021)
- [Dynamic Group Detection using VLM-augmented Temporal Groupness Graph](https://mlsanity.com/paper/2509.04758/) (2025)
- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [Efficient Large-Scale Face Clustering Using an Online Mixture of Gaussians](https://mlsanity.com/paper/2103.17272/) (2021)
- [Boosting Semi-Supervised Face Recognition with Noise Robustness](https://mlsanity.com/paper/2105.04431/) (2021)
- [Image Clustering using Restricted Boltzman Machine](https://mlsanity.com/paper/2312.13845/) (2023)
- [An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better?](https://mlsanity.com/paper/2211.05183/) (2022)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [A Linkage-based Doubly Imbalanced Graph Learning Framework for Face Clustering](https://mlsanity.com/paper/2107.02477/) (2021)
- [Density-Based Clustering with Kernel Diffusion](https://mlsanity.com/paper/2110.05096/) (2021)

## Abstract (arXiv)

Face recognition has witnessed great progress in recent years, mainly attributed to the high-capacity model designed and the abundant labeled data collected. However, it becomes more and more prohibitive to scale up the current million-level identity annotations. In this work, we show that unlabeled face data can be as effective as the labeled ones. Here, we consider a setting closely mimicking the real-world scenario, where the unlabeled data are collected from unconstrained environments and their identities are exclusive from the labeled ones. Our main insight is that although the class information is not available, we can still faithfully approximate these semantic relationships by constructing a relational graph in a bottom-up manner. We propose Consensus-Driven Propagation (CDP) to tackle this challenging problem with two modules, the "committee" and the "mediator", which select positive face pairs robustly by carefully aggregating multi-view information. Extensive experiments validate the effectiveness of both modules to discard outliers and mine hard positives. With CDP, we achieve a compelling accuracy of 78.18% on MegaFace identification challenge by using only 9% of the labels, comparing to 61.78% when no unlabeled data are used and 78.52% when all labels are employed.