Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes

• URL: http://arxiv.org/abs/2103.13225v1
• Date: Wed, 24 Mar 2021 14:34:26 GMT
• Title: Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes
• Authors: Shuai Shen, Wanhua Li, Zheng Zhu, Guan Huang, Dalong Du, Jiwen Lu, Jie Zhou
• Abstract summary: We propose a structure-preserved subgraph sampling strategy to explore the power of large-scale training data. The STAR-FC gets 91.97 pairwise F-score on partial MS1M within 310s which surpasses the state-of-the-arts.
• Score: 76.6700928596238
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Face clustering is a promising method for annotating unlabeled face images. Recent supervised approaches have boosted the face clustering accuracy greatly, however their performance is still far from satisfactory. These methods can be roughly divided into global-based and local-based ones. Global-based methods suffer from the limitation of training data scale, while local-based ones are difficult to grasp the whole graph structure information and usually take a long time for inference. Previous approaches fail to tackle these two challenges simultaneously. To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method. Specifically, we design a structure-preserved subgraph sampling strategy to explore the power of large-scale training data, which can increase the training data scale from ${10^{5}}$ to ${10^{7}}$. During inference, the STAR-FC performs efficient full-graph clustering with two steps: graph parsing and graph refinement. And the concept of node intimacy is introduced in the second step to mine the local structural information. The STAR-FC gets 91.97 pairwise F-score on partial MS1M within 310s which surpasses the state-of-the-arts. Furthermore, we are the first to train on very large-scale graph with 20M nodes, and achieve superior inference results on 12M testing data. Overall, as a simple and effective method, the proposed STAR-FC provides a strong baseline for large-scale face clustering. Code is available at \url{https://sstzal.github.io/STAR-FC/}.

Related papers

• Self-Supervised Contrastive Graph Clustering Network via Structural Information Fusion [15.293684479404092]
  We propose a novel deep graph clustering method called CGCN. Our approach introduces contrastive signals and deep structural information into the pre-training process. Our method has been experimentally validated on multiple real-world graph datasets.
  arXiv  Detail & Related papers  (2024-08-08T09:49:26Z)
• Amplify Graph Learning for Recommendation via Sparsity Completion [16.32861024767423]
  Graph learning models have been widely deployed in collaborative filtering (CF) based recommendation systems. Due to the issue of data sparsity, the graph structure of the original input lacks potential positive preference edges. We propose an Amplify Graph Learning framework based on Sparsity Completion (called AGL-SC)
  arXiv  Detail & Related papers  (2024-06-27T08:26:20Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited [51.24526202984846]
  Graph-based semi-supervised learning (GSSL) has long been a hot research topic. graph convolutional networks (GCNs) have become the predominant techniques for their promising performance.
  arXiv  Detail & Related papers  (2023-09-24T10:10:21Z)
• Dink-Net: Neural Clustering on Large Graphs [59.10189693120368]
  A deep graph clustering method (Dink-Net) is proposed with the idea of dilation and shrink. By discriminating nodes, whether being corrupted by augmentations, representations are learned in a self-supervised manner. The clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss. Compared to the runner-up, Dink-Net 9.62% achieves NMI improvement on the ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges.
  arXiv  Detail & Related papers  (2023-05-28T15:33:24Z)
• Fine-grained Graph Learning for Multi-view Subspace Clustering [2.4094285826152593]
  We propose a fine-grained graph learning framework for multi-view subspace clustering (FGL-MSC) The main challenge is how to optimize the fine-grained fusion weights while generating the learned graph that fits the clustering task. Experiments on eight real-world datasets show that the proposed framework has comparable performance to the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-01-12T18:00:29Z)
• Git: Clustering Based on Graph of Intensity Topology [25.679620842010422]
  We propose a novel clustering algorithm, namely GIT (Clustering Based on textbfGraph of textbfIntensity textbfTopology) With fast local cluster detection, robust topo-graph construction and accurate edge-cutting, GIT shows attractive ARISE performance.
  arXiv  Detail & Related papers  (2021-10-04T09:29:43Z)
• Structured Graph Learning for Clustering and Semi-supervised Classification [74.35376212789132]
  We propose a graph learning framework to preserve both the local and global structure of data. Our method uses the self-expressiveness of samples to capture the global structure and adaptive neighbor approach to respect the local structure. Our model is equivalent to a combination of kernel k-means and k-means methods under certain condition.
  arXiv  Detail & Related papers  (2020-08-31T08:41:20Z)
• Learning to Cluster Faces via Confidence and Connectivity Estimation [136.5291151775236]
  We propose a fully learnable clustering framework without requiring a large number of overlapped subgraphs. Our method significantly improves clustering accuracy and thus performance of the recognition models trained on top, yet it is an order of magnitude more efficient than existing supervised methods.
  arXiv  Detail & Related papers  (2020-04-01T13:39:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.