mlsanityData to 14 Oct 2026

Bootstrap Deep Spectral Clustering with Optimal Transport

arXiv 2508.04200 ↗First posted 6 Aug 2025cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Spectral clustering is a leading clustering method. Two of its major shortcomings are the disjoint optimization process and the limited representation capacity. To address these issues, we propose a deep spectral clustering model (named BootSC), which jointly learns all stages of spectral clustering -- affinity matrix construction, spectral embedding, and k-means clustering -- using a single network in an end-to-end manner. BootSC leverages effective and efficient optimal-transport-derived supervision to bootstrap the affinity matrix and the cluster assignment matrix. Moreover, a semantically-consistent orthogonal re-parameterization technique is introduced to orthogonalize spectral embeddings, significantly enhancing the discrimination capability. Experimental results indicate that BootSC achieves state-of-the-art clustering performance. For example, it accomplishes a notable 16% NMI improvement over the runner-up method on the challenging ImageNet-Dogs dataset. Our code is available at https://github.com/spdj2271/BootSC.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 45 of its 109 references that are in the map. First posted on arXiv 6 Aug 2025.

Builds on

45 of 109 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  10. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  11. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  12. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
33 more
  1. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  2. 2019Self-labelling via simultaneous clustering and representation learningcited by 528
  3. 2015Optimal Transport for Domain Adaptationcited by 463
  4. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  5. 2020SCAN: Learning to Classify Images without Labelscited by 352
  6. 2020Contrastive Clusteringcited by 265
  7. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
  8. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  9. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  10. 2017Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimizationcited by 113
  11. 2020Online Deep Clustering for Unsupervised Representation Learningcited by 100
  12. 2017Deep Subspace Clustering Networkscited by 94
  13. 2018SpectralNet: Spectral Clustering using Deep Neural Networkscited by 94
  14. 2019Deep Comprehensive Correlation Mining for Image Clusteringcited by 80
  15. 2023Large Language Models Enable Few-Shot Clusteringcited by 72
  16. 2019Deep Spectral Clustering using Dual Autoencoder Networkcited by 71
  17. 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 70
  18. 2021Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelationcited by 65
  19. 2021Graph Contrastive Clusteringcited by 61
  20. 2022HCSC: Hierarchical Contrastive Selective Codingcited by 43
  21. 2021You Never Cluster Alonecited by 38
  22. 2023Image Clustering Conditioned on Text Criteriacited by 26
  23. 2023Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarioscited by 19
  24. 2023DivClust: Controlling Diversity in Deep Clusteringcited by 18
  25. 2017CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Datacited by 16
  26. 2021Consistent Multiple Graph Embedding for Multi-View Clusteringcited by 12
  27. 2021Deep Embedded K-Means Clusteringcited by 12
  28. 2019Spectral Clustering via Ensemble Deep Autoencoder Learning (SC-EDAE)cited by 10
  29. 2017Unified Spectral Clustering with Optimal Graphcited by 5
  30. 2023Acoustic Scene Clustering Using Joint Optimization of Deep Embedding Learning and Clustering Iterationcited by 4
  31. 2024Deep Spectral Clustering via Joint Spectral Embedding and Kmeanscited by 4
  32. 2016Mini-Batch Spectral Clusteringcited by 3
  33. 2021Network Embedding via Deep Prediction Modelcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025On the Provable Importance of Gradients for Language-Assisted Image Clusteringcited by 8
  2. 2026Delving into Spectral Clustering with Vision-Language Representationscited by 2