mlsanityData to 14 Oct 2026

DeepDPM: Deep Clustering With an Unknown Number of Clusters

arXiv 2203.14309 ↗First posted 27 Mar 2022cs.LG stat.MLcited by 52

Not on the map. Why?

Abstract (arXiv)

Deep Learning (DL) has shown great promise in the unsupervised task of clustering. That said, while in classical (i.e., non-deep) clustering the benefits of the nonparametric approach are well known, most deep-clustering methods are parametric: namely, they require a predefined and fixed number of clusters, denoted by K. When K is unknown, however, using model-selection criteria to choose its optimal value might become computationally expensive, especially in DL as the training process would have to be repeated numerous times. In this work, we bridge this gap by introducing an effective deep-clustering method that does not require knowing the value of K as it infers it during the learning. Using a split/merge framework, a dynamic architecture that adapts to the changing K, and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones). While the very few existing deep nonparametric methods lack scalability, we demonstrate ours by being the first to report the performance of such a method on ImageNet. We also demonstrate the importance of inferring K by showing how methods that fix it deteriorate in performance when their assumed K value gets further from the ground-truth one, especially on imbalanced datasets. Our code is available at https://github.com/BGU-CS-VIL/DeepDPM.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 17 of its 76 references that are in the map. First posted on arXiv 27 Mar 2022.

Builds on

17 of 76 references.

References · 17

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  5. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  6. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  7. 2020SCAN: Learning to Classify Images without Labelscited by 352
  8. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
  9. 2019Graph Embedded Pose Clustering for Anomaly Detectioncited by 95
  10. 2019N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embeddingcited by 30
  11. 2018Deep Continuous Clusteringcited by 21
  12. 2019Video Face Clustering with Unknown Number of Clusterscited by 17
5 more
  1. 2016Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixturescited by 9
  2. 2015Deep Learning with Nonparametric Clusteringcited by 6
  3. 2022Sampling in Dirichlet Process Mixture Models for Clustering Streaming Datacited by 6
  4. 2016Small-Variance Nonparametric Clustering on the Hyperspherecited by 3
  5. 2022Common Failure Modes of Subcluster-based Sampling in Dirichlet Process Gaussian Mixture Models -- and a Deep-learning Solutioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 8; 2024: 16; 2025: 13; 2026: 10.

52 papers.

Sort:

By area:

  1. 2024Wavelet Convolutions for Large Receptive Fieldscited by 74
  2. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  3. 2022Visual Recognition with Deep Nearest Centroidscited by 59
  4. 2023Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discoverycited by 16
  5. 2023Reinforcement Graph Clustering with Unknown Cluster Numbercited by 16
  6. 2023Open-world Semi-supervised Novel Class Discoverycited by 15
  7. 2025Learning Clustering-based Prototypes for Compositional Zero-shot Learningcited by 14
  8. 2024P2OT: Progressive Partial Optimal Transport for Deep Imbalanced Clusteringcited by 13
  9. 2024Neural Clustering based Visual Representation Learningcited by 12
  10. 2022e-CLIP: Large-Scale Vision-Language Representation Learning in E-commercecited by 10
  11. 2024End-to-end Learnable Clustering for Intent Learning in Recommendationcited by 10
  12. 2023What's in a Name? Beyond Class Indices for Image Recognitioncited by 9
38 more
  1. 2025BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Predictioncited by 9
  2. 2024Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrencecited by 6
  3. 2022Generalised Mutual Information for Discriminative Clusteringcited by 5
  4. 2024An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoderscited by 5
  5. 2024cDP-MIL: Robust Multiple Instance Learning via Cascaded Dirichlet Processcited by 5
  6. 2024PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysiscited by 5
  7. 2025Riemannian Optimization on Relaxed Indicator Matrix Manifoldcited by 5
  8. 2024ALPS: An Auto-Labeling and Pre-training Scheme for Remote Sensing Segmentation With Segment Anything Modelcited by 4
  9. 2024Dying Clusters Is All You Need -- Deep Clustering With an Unknown Number of Clusterscited by 4
  10. 2023PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extractioncited by 3
  11. 2025Clustering via Self-Supervised Diffusioncited by 3
  12. 2026TDEC: Deep Embedded Image Clustering with Transformer and Distribution Informationcited by 3
  13. 2024Deep Embedding Clustering Driven by Sample Stabilitycited by 2
  14. 2024SP2OT: Semantic-Regularized Progressive Partial Optimal Transport for Imbalanced Clusteringcited by 2
  15. 2024Deep Online Probability Aggregation Clusteringcited by 2
  16. 2026Deep Clustering with Associative Memoriescited by 2
  17. 2023DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-Encodercited by 1
  18. 2023Generalised Mutual Information: a Framework for Discriminative Clusteringcited by 1
  19. 2025Consistent Amortized Clustering via Generative Flow Networkscited by 1
  20. 2025Advancing Local Clustering on Graphs via Compressive Sensing: Semi-supervised and Unsupervised Methodscited by 1
  21. 2025Online Clustering of Seafloor Imagery for Interpretation during Long-Term AUV Operationscited by 1
  22. 2025FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videoscited by 1
  23. 2026A Federated Generalized Expectation-Maximization Algorithm for Mixture Models with an Unknown Number of Componentscited by 1
  24. 2026Deep Image Clustering Based on Curriculum Learning and Density Informationcited by 1
  25. 2022Clustering Optimisation Method for Highly Connected Biological Datacited by 0
  26. 2022MGTCOM: Community Detection in Multimodal Graphscited by 0
  27. 2024Masked AutoEncoder for Graph Clustering without Pre-defined Cluster Number kcited by 0
  28. 2024Deep Clustering Evaluation: How to Validate Internal Clustering Validation Measurescited by 0
  29. 2024Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learningcited by 0
  30. 2025Utilization of Neighbor Information for Image Classification with Different Levels of Supervisioncited by 0
  31. 2025A Tutorial on Discriminative Clustering and Mutual Informationcited by 0
  32. 2025ADAM: Autonomous Discovery and Annotation Model using LLMs for Context-Aware Annotationscited by 0
  33. 2025DECOR: Deep Embedding Clustering with Orientation Robustnesscited by 0
  34. 2025Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)cited by 0
  35. 2026Khatri-Rao Clustering for Data Summarizationcited by 0
  36. 2026Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Corescited by 0
  37. 2026Hierarchical ODE: Learning Continuous-Time Physical Prototypes for Early Link Failure Detectioncited by 0
  38. 2026Knowledge Reutilization in Meta-Reinforcement Learningcited by 0

50 most cited of 52 All 52 (JSON)