Learn to Cluster Faces via Pairwise Classification

TL;DR

This paper introduces a pairwise classification approach for face clustering that reduces memory usage and improves efficiency, outperforming graph-based methods on benchmarks.

Contribution

It formulates face clustering as a pairwise relationship classification task, avoiding large-scale graph memory issues and incorporating contextual information for better accuracy.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Demonstrates faster clustering speeds compared to existing methods.

Uses less memory than traditional graph-based clustering approaches.

Abstract

Face clustering plays an essential role in exploiting massive unlabeled face data. Recently, graph-based face clustering methods are getting popular for their satisfying performances. However, they usually suffer from excessive memory consumption especially on large-scale graphs, and rely on empirical thresholds to determine the connectivities between samples in inference, which restricts their applications in various real-world scenes. To address such problems, in this paper, we explore face clustering from the pairwise angle. Specifically, we formulate the face clustering task as a pairwise relationship classification task, avoiding the memory-consuming learning on large-scale graphs. The classifier can directly determine the relationship between samples and is enhanced by taking advantage of the contextual information. Moreover, to further facilitate the efficiency of our method, we propose a rank-weighted density to guide the selection of pairs sent to the classifier. Experimental results demonstrate that our method achieves state-of-the-art performances on several public clustering benchmarks at the fastest speed and shows a great advantage in comparison with graph-based clustering methods on memory consumption.