Efficient Large-Scale Face Clustering Using an Online Mixture of Gaussians
This work addresses the problem of efficiently clustering faces in real-time streams for applications like surveillance or social media, though it appears incremental as it builds on existing mixture models.
The authors tackled large-scale online face clustering by proposing an online Gaussian mixture-based method (OGMC) that represents identities with multiple clusters and updates connections dynamically, achieving superior accuracy, efficiency, and scalability compared to state-of-the-art methods on benchmarks.
In this work, we address the problem of large-scale online face clustering: given a continuous stream of unknown faces, create a database grouping the incoming faces by their identity. The database must be updated every time a new face arrives. In addition, the solution must be efficient, accurate and scalable. For this purpose, we present an online gaussian mixture-based clustering method (OGMC). The key idea of this method is the proposal that an identity can be represented by more than just one distribution or cluster. Using feature vectors (f-vectors) extracted from the incoming faces, OGMC generates clusters that may be connected to others depending on their proximity and their robustness. Every time a cluster is updated with a new sample, its connections are also updated. With this approach, we reduce the dependency of the clustering process on the order and the size of the incoming data and we are able to deal with complex data distributions. Experimental results show that the proposed approach outperforms state-of-the-art clustering methods on large-scale face clustering benchmarks not only in accuracy, but also in efficiency and scalability.