On Mitigating Hard Clusters for Face Clustering

• URL: http://arxiv.org/abs/2207.11895v1
• Date: Mon, 25 Jul 2022 03:55:15 GMT
• Title: On Mitigating Hard Clusters for Face Clustering
• Authors: Yingjie Chen, Huasong Zhong, Chong Chen, Chen Shen, Jianqiang Huang, Tao Wang, Yun Liang, Qianru Sun
• Abstract summary: Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. We introduce two novel modules, Neighborhood-Diffusion-based Density (NDDe) and Transition-Probability-based Distance (TPDi) Our experiments on multiple benchmarks show that each module contributes to the final performance of our method.
• Score: 48.39472979642971
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard clusters, which is caused by the heterogeneity, \ie, high variations in size and sparsity, of the clusters. Consequently, the conventional way of using a uniform threshold (to identify clusters) often leads to a terrible misclassification for the samples that should belong to hard clusters. We tackle this problem by leveraging the neighborhood information of samples and inferring the cluster memberships (of samples) in a probabilistic way. We introduce two novel modules, Neighborhood-Diffusion-based Density (NDDe) and Transition-Probability-based Distance (TPDi), based on which we can simply apply the standard Density Peak Clustering algorithm with a uniform threshold. Our experiments on multiple benchmarks show that each module contributes to the final performance of our method, and by incorporating them into other advanced face clustering methods, these two modules can boost the performance of these methods to a new state-of-the-art. Code is available at: https://github.com/echoanran/On-Mitigating-Hard-Clusters.

Related papers

• Stable Cluster Discrimination for Deep Clustering [7.175082696240088]
  Deep clustering can optimize representations of instances (i.e., representation learning) and explore the inherent data distribution. The coupled objective implies a trivial solution that all instances collapse to the uniform features. In this work, we first show that the prevalent discrimination task in supervised learning is unstable for one-stage clustering. A novel stable cluster discrimination (SeCu) task is proposed and a new hardness-aware clustering criterion can be obtained accordingly.
  arXiv  Detail & Related papers  (2023-11-24T06:43:26Z)
• Deep Multi-View Subspace Clustering with Anchor Graph [11.291831842959926]
  We propose a novel deep multi-view subspace clustering method with anchor graph (DMCAG) DMCAG learns the embedded features for each view independently, which are used to obtain the subspace representations. Our method achieves superior clustering performance over other state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-11T16:17:43Z)
• Distributed Solution of the Inverse Rig Problem in Blendshape Facial Animation [0.0]
  Rig inversion is central in facial animation as it allows for a realistic and appealing performance of avatars. A possible approach towards a faster solution is clustering, which exploits the spacial nature of the face. In this paper, we go a step further, involving cluster coupling to get more confident estimates of the overlapping components.
  arXiv  Detail & Related papers  (2023-03-11T10:34:07Z)
• Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning [146.11600461034746]
  Method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. We prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
  arXiv  Detail & Related papers  (2022-09-27T19:04:36Z)
• Implicit Sample Extension for Unsupervised Person Re-Identification [97.46045935897608]
  Clustering sometimes mixes different true identities together or splits the same identity into two or more sub clusters. We propose an Implicit Sample Extension (OurWholeMethod) method to generate what we call support samples around the cluster boundaries. Experiments demonstrate that the proposed method is effective and achieves state-of-the-art performance for unsupervised person Re-ID.
  arXiv  Detail & Related papers  (2022-04-14T11:41:48Z)
• Clustering by Maximizing Mutual Information Across Views [62.21716612888669]
  We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method significantly outperforms state-of-the-art single-stage clustering methods across a variety of image datasets.
  arXiv  Detail & Related papers  (2021-07-24T15:36:49Z)
• Efficient Large-Scale Face Clustering Using an Online Mixture of Gaussians [1.3101369903953806]
  We present an online gaussian mixture-based clustering method (OGMC) for large-scale online face clustering. Using feature vectors (f-vectors) extracted from the incoming faces, OGMC generates clusters that may be connected to others depending on their proximity and robustness. Experimental results show that the proposed approach outperforms state-of-the-art clustering methods on large-scale face clustering benchmarks.
  arXiv  Detail & Related papers  (2021-03-31T17:59:38Z)
• Scalable Hierarchical Agglomerative Clustering [65.66407726145619]
  Existing scalable hierarchical clustering methods sacrifice quality for speed. We present a scalable, agglomerative method for hierarchical clustering that does not sacrifice quality and scales to billions of data points.
  arXiv  Detail & Related papers  (2020-10-22T15:58:35Z)
• 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.