Learning to Cluster Faces on an Affinity Graph
arXiv:1904.02749
Abstract
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level. Taking it to a next level requires substantially larger data, which would involve prohibitive annotation cost. Hence, exploiting unlabeled data becomes an appealing alternative. Recent works have shown that clustering unlabeled faces is a promising approach, often leading to notable performance gains. Yet, how to effectively cluster, especially on a large-scale (i.e. million-level or above) dataset, remains an open question. A key challenge lies in the complex variations of cluster patterns, which make it difficult for conventional clustering methods to meet the needed accuracy. This work explores a novel approach, namely, learning to cluster instead of relying on hand-crafted criteria. Specifically, we propose a framework based on graph convolutional network, which combines a detection and a segmentation module to pinpoint face clusters. Experiments show that our method yields significantly more accurate face clusters, which, as a result, also lead to further performance gain in face recognition.
8 pages, 8 figures, CVPR 2019
References in corpus (6)
- Inductive Representation Learning on Large Graphs
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
- Rich feature hierarchies for accurate object detection and semantic segmentation
- CosFace: Large Margin Cosine Loss for Deep Face Recognition
- MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
- Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition