Face Clustering: Representation And Pairwise Constraints

Abstract

Clustering face images according to their identity has two important applications: (i) grouping a collection of face images when no external labels are associated with images, and (ii) indexing for efficient large scale face retrieval. The clustering problem is composed of two key parts: face representation and choice of similarity for grouping faces. We first propose a representation based on ResNet, which has been shown to perform very well in image classification problems. Given this representation, we design a clustering algorithm, Conditional Pairwise Clustering (ConPaC), which directly estimates the adjacency matrix only based on the similarity between face images. This allows a dynamic selection of number of clusters and retains pairwise similarity between faces. ConPaC formulates the clustering problem as a Conditional Random Field (CRF) model and uses Loopy Belief Propagation to find an approximate solution for maximizing the posterior probability of the adjacency matrix. Expe

Stats

• citations87
• S2 citations—
• github stars0
• HF likes0
• heat score14.58
• arxiv keyshi2017face

Related papers

• A Distributed Approximate Nearest Neighbor Method For Real-time Face Recognition (2020)0.00
• Faircop: Facial Image Retrieval Using Contrastive Personalization (2022)0.00
• Learning Discrete Representations Via Constrained Clustering For Effective And Efficient Dense Retrieval (2021)11.39
• Cross-view Kernel Similarity Metric Learning Using Pairwise Constraints For Person Re-identification (2019)0.00
• Deep Constrained Dominant Sets For Person Re-identification (2019)9.23
• Local Directional Relation Pattern For Unconstrained And Robust Face Retrieval (2017)11.85
• Unicom: Universal And Compact Representation Learning For Image Retrieval (2023)5.70
• Deep Co-attention Based Comparators For Relative Representation Learning In Person Re-identification (2018)13.34