Learn to Cluster Faces via Pairwise Classification

@article{Liu2021LearnTC,
  title={Learn to Cluster Faces via Pairwise Classification},
  author={Junfu Liu and Di Qiu and Pengfei Yan and Xiaolin Wei},
  journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2021},
  pages={3825-3833}
}
  • Junfu Liu, Di Qiu, Xiaolin Wei
  • Published 1 October 2021
  • Computer Science
  • 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
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… 
On Mitigating Hard Clusters for Face Clustering
TLDR
Two novel modules are introduced, Neighborhood-Diffusion-based Density (NDDe) and Transition-Probability-based Distance (TPDi), based on which the standard Density Peak Clustering algorithm can be applied with a uniform threshold, to tackle the problem of identifying small or sparse face image clusters.
FaceMap: Towards Unsupervised Face Clustering via Map Equation
TLDR
Inspired by observations on the ranked transition probabilities in the affinity graph constructed from facial images, an outlier detection strategy to adaptively adjust transition probabilities among images is developed.

References

SHOWING 1-10 OF 34 REFERENCES
Learning to Cluster Faces via Confidence and Connectivity Estimation
TLDR
This paper proposes a fully learnable clustering framework without requiring a large number of overlapped subgraphs, and transforms the clustering problem into two sub-problems, designed to estimate the confidence of vertices and the connectivity of edges, respectively.
Learning to Cluster Faces on an Affinity Graph
TLDR
This work explores a novel approach, namely, learning to cluster instead of relying on hand-crafted criteria, and proposes a framework based on graph convolutional network, which combines a detection and a segmentation module to pinpoint face clusters.
Linkage Based Face Clustering via Graph Convolution Network
TLDR
This paper presents an accurate and scalable approach to the face clustering task, and shows that the proposed method does not need the number of clusters as prior, is aware of noises and outliers, and can be extended to a multi-view version for more accurate clustering accuracy.
Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
TLDR
It is shown that unlabeled face data can be as effective as the labeled ones, and Consensus-Driven Propagation (CDP) is proposed 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.
FaceNet: A unified embedding for face recognition and clustering
TLDR
A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
Face Clustering: Representation and Pairwise Constraints
TLDR
A clustering algorithm, Conditional Pairwise Clustering (ConPaC), which directly estimates the adjacency matrix only based on the similarities between face images, and can naturally incorporate pairwise constraints to work in a semi-supervised way that leads to improved clustering performance.
Density-Aware Feature Embedding for Face Clustering
TLDR
This paper proposes a Density-Aware Feature Embedding Network (DA-Net) for the task of face clustering, which utilizes both local and non-local information, to learn a robust feature embedding.
Clustering Millions of Faces by Identity
TLDR
An approximate Rank-Order clustering algorithm is presented that performs better than popular clustering algorithms (k-Means and Spectral) and an internal per-cluster quality measure is developed to rank individual clusters for manual exploration of high quality clusters that are compact and isolated.
Merge or Not? Learning to Group Faces via Imitation Learning
TLDR
A novel face grouping framework that learns clustering strategy from ground-truth simulated behavior through imitation learning and makes sequential decision to dynamically decide when to merge two face instances/groups driven by short- and long-term rewards.
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
TLDR
A benchmark task to recognize one million celebrities from their face images, by using all the possibly collected face images of this individual on the web as training data, which could lead to one of the largest classification problems in computer vision.
...
...