mlsanityData to 14 Oct 2026

Incremental Generalized Category Discovery

arXiv 2304.14310 ↗First posted 27 Apr 2023cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

We explore the problem of Incremental Generalized Category Discovery (IGCD). This is a challenging category incremental learning setting where the goal is to develop models that can correctly categorize images from previously seen categories, in addition to discovering novel ones. Learning is performed over a series of time steps where the model obtains new labeled and unlabeled data, and discards old data, at each iteration. The difficulty of the problem is compounded in our generalized setting as the unlabeled data can contain images from categories that may or may not have been observed before. We present a new method for IGCD which combines non-parametric categorization with efficient image sampling to mitigate catastrophic forgetting. To quantify performance, we propose a new benchmark dataset named iNatIGCD that is motivated by a real-world fine-grained visual categorization task. In our experiments we outperform existing related methods

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 48 of its 69 references that are in the map. First posted on arXiv 27 Apr 2023.

Builds on

48 of 69 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  9. 2020Supervised Contrastive Learningcited by 2,829
  10. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  11. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  12. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
36 more
  1. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  2. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  3. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  4. 2015Towards Open Set Deep Networkscited by 538
  5. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  6. 2018Recent Advances in Open Set Recognition: A Surveycited by 310
  7. 2022Masked Siamese Networks for Label-Efficient Learningcited by 302
  8. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  9. 2014Towards Open World Recognitioncited by 226
  10. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 225
  11. 2022Generalized Category Discoverycited by 211
  12. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 168
  13. 2021Open-World Semi-Supervised Learningcited by 165
  14. 2021A Unified Objective for Novel Class Discoverycited by 162
  15. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 143
  16. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  17. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  18. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
  19. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  20. 2019Multi-class Classification without Multi-class Labelscited by 100
  21. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 87
  22. 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
  23. 2022XCon: Learning with Experts for Fine-grained Category Discoverycited by 50
  24. 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
  25. 2022Class-incremental Novel Class Discoverycited by 42
  26. 2021Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learningcited by 40
  27. 2022Novel Class Discovery without Forgettingcited by 39
  28. 2022Parametric Information Maximization for Generalized Category Discoverycited by 39
  29. 2022Grow and Merge: A Unified Framework for Continuous Categories Discoverycited by 33
  30. 2019Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognitioncited by 26
  31. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  32. 2023GeoNet: Benchmarking Unsupervised Adaptation across Geographiescited by 17
  33. 2020Density-Aware Graph for Deep Semi-Supervised Visual Recognitioncited by 15
  34. 2022Continual Learning with Evolving Class Ontologiescited by 13
  35. 2023Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discoverycited by 11
  36. 2023Taxonomic Class Incremental Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 8; 2025: 7; 2026: 4.

25 papers.

Sort:

By area:

  1. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  2. 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
  3. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  4. 2024HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shiftscited by 23
  5. 2024Happy: A Debiased Learning Framework for Continual Generalized Category Discoverycited by 18
  6. 2024Effective Prompt Pool Learning for Continual Category Discoverycited by 14
  7. 2025MOS: Modeling Object-Scene Associations in Generalized Category Discoverycited by 10
  8. 2025Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discoverycited by 10
  9. 2024Contextuality Helps Representation Learning for Generalized Category Discoverycited by 6
  10. 2023Category Adaptation Meets Projected Distillation in Generalized Continual Category Discoverycited by 5
  11. 2025Category Discovery: An Open-World Perspectivecited by 5
  12. 2023Generalized Category Discovery in Semantic Segmentationcited by 4
13 more
  1. 2023Federated Continual Novel Class Learningcited by 4
  2. 2024Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discoverycited by 4
  3. 2024Labeled Data Selection for Category Discoverycited by 4
  4. 2024DIG-FACE: De-biased Learning for Generalized Facial Expression Category Discoverycited by 3
  5. 2026SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discoverycited by 3
  6. 2024A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorizationcited by 2
  7. 2025Proxy-Anchor and EVT-Driven Continual Learning Method for Generalized Category Discoverycited by 1
  8. 2026TALON: Test-time Adaptive Learning for On-the-Fly Category Discoverycited by 1
  9. 2025Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discoverycited by 0
  10. 2025OpenHAIV: A Framework Towards Practical Open-World Learningcited by 0
  11. 2025Hierarchical Generalized Category Discovery for Brain Tumor Classification in Digital Pathologycited by 0
  12. 2026Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discoverycited by 0
  13. 2026Unlocking Optical Prior: Spectrum-Guided Knowledge Transfer for SAR Generalized Category Discoverycited by 0