mlsanityData to 7 Oct 2026

Contrastive Mean-Shift Learning for Generalized Category Discovery

arXiv 2404.09451 ↗First posted 15 Apr 2024cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

We address the problem of generalized category discovery (GCD) that aims to partition a partially labeled collection of images; only a small part of the collection is labeled and the total number of target classes is unknown. To address this generalized image clustering problem, we revisit the mean-shift algorithm, i.e., a classic, powerful technique for mode seeking, and incorporate it into a contrastive learning framework. The proposed method, dubbed Contrastive Mean-Shift (CMS) learning, trains an image encoder to produce representations with better clustering properties by an iterative process of mean shift and contrastive update. Experiments demonstrate that our method, both in settings with and without the total number of clusters being known, achieves state-of-the-art performance on six public GCD benchmarks without bells and whistles.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 34 of its 64 references that are in the map. First posted on arXiv 15 Apr 2024.

Builds on

34 of 64 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2020Supervised Contrastive Learningcited by 2,803
  10. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  11. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  12. 2016An overview of gradient descent optimization algorithmscited by 1,021
22 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  3. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  4. 2022Generalized Category Discoverycited by 209
  5. 2019Local Aggregation for Unsupervised Learning of Visual Embeddingscited by 204
  6. 2021Open-World Semi-Supervised Learningcited by 165
  7. 2021A Unified Objective for Novel Class Discoverycited by 161
  8. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
  9. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
  10. 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 90
  11. 2022PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discoverycited by 85
  12. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  13. 2021Mean Shift for Self-Supervised Learningcited by 65
  14. 2019The Herbarium Challenge 2019 Datasetcited by 59
  15. 2017Recurrent Pixel Embedding for Instance Groupingcited by 57
  16. 2022Parametric Information Maximization for Generalized Category Discoverycited by 39
  17. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  18. 2021Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillationcited by 23
  19. 2021MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Trackingcited by 9
  20. 2016Mixture model modal clusteringcited by 8
  21. 2023Convergence Analysis of Mean Shiftcited by 6
  22. 2022GridShift: A Faster Mode-seeking Algorithm for Image Segmentation and Object Trackingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 19; 2026: 14.

39 papers.

Sort:

  1. 2024In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentationcited by 38
  2. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  3. 2025Hyperbolic Category Discoverycited by 20
  4. 2025Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancementcited by 13
  5. 2025Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstructioncited by 13
  6. 2025MOS: Modeling Object-Scene Associations in Generalized Category Discoverycited by 10
  7. 2024Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discoverycited by 9
  8. 2025Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularizationcited by 6
  9. 2025When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approachcited by 5
  10. 2025Consistent Supervised-Unsupervised Alignment for Generalized Category Discoverycited by 5
  11. 2025Category Discovery: An Open-World Perspectivecited by 5
  12. 2024DIG-FACE: De-biased Learning for Generalized Facial Expression Category Discoverycited by 3
27 more
  1. 2025Generalized Category Discovery via Token Manifold Capacity Learningcited by 3
  2. 2025A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attentioncited by 3
  3. 2025Open Ad-hoc Categorization with Contextualized Feature Learningcited by 3
  4. 2024AdaptGCD: Multi-Expert Adapter Tuning for Generalized Category Discoverycited by 2
  5. 2025Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Expertscited by 2
  6. 2025HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discoverycited by 2
  7. 2024Composing Novel Classes: A Concept-Driven Approach to Generalized Category Discoverycited by 1
  8. 2025Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancementcited by 1
  9. 2025FaceGCD: Generalized Face Discovery via Dynamic Prefix Generationcited by 1
  10. 2025Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learningcited by 1
  11. 2025Sharpness-aware Dynamic Anchor Selection for Generalized Category Discoverycited by 1
  12. 2026GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discoverycited by 1
  13. 2026TALON: Test-time Adaptive Learning for On-the-Fly Category Discoverycited by 1
  14. 2026Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discoverycited by 1
  15. 2025Component Adaptive Clustering for Generalized Category Discoverycited by 0
  16. 2025Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labelscited by 0
  17. 2026InfoSculpt: Sculpting the Latent Space for Generalized Category Discoverycited by 0
  18. 2026SIEFormer: Spectral-Interpretable and -Enhanced Transformer for Generalized Category Discoverycited by 0
  19. 2026FOCUS: Bridging Fine-Grained Recognition and Open-World Discovery across Domainscited by 0
  20. 2026Learning Like Humans: Analogical Concept Learning for Generalized Category Discoverycited by 0
  21. 2026The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discoverycited by 0
  22. 2026OmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticismcited by 0
  23. 2026Unlocking Optical Prior: Spectrum-Guided Knowledge Transfer for SAR Generalized Category Discoverycited by 0
  24. 2026Identifying Latent Concepts and Structures for Generalized Category Discoverycited by 0
  25. 2026Fourier Self-Supervision for Fine-Grained Generalized Category Discoverycited by 0
  26. 2026CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalizationcited by 0
  27. 2026Generalized Biomedicine Discoverycited by 0