mlsanityData to 7 Oct 2026

Class-incremental Novel Class Discovery

arXiv 2207.08605 ↗First posted 18 Jul 2022cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data set containing disjoint yet related categories. Apart from discovering novel classes, we also aim at preserving the ability of the model to recognize previously seen base categories. Inspired by rehearsal-based incremental learning methods, in this paper we propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes by jointly exploiting base class feature prototypes and feature-level knowledge distillation. We also propose a self-training clustering strategy that simultaneously clusters novel categories and trains a joint classifier for both the base and novel classes. This makes our method able to operate in a class-incremental setting. Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches. Code is available at https://github.com/OatmealLiu/class-iNCD

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

28 of 37 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  7. 2016Learning without Forgettingcited by 2,465
  8. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  9. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  10. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  11. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  12. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
16 more
  1. 2019Large Scale Incremental Learningcited by 727
  2. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  3. 2018End-to-End Incremental Learningcited by 596
  4. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  5. 2019On Tiny Episodic Memories in Continual Learningcited by 299
  6. 2018Learning without Memorizingcited by 249
  7. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  8. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  9. 2021A Unified Objective for Novel Class Discoverycited by 161
  10. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
  11. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  12. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  13. 2019Multi-class Classification without Multi-class Labelscited by 100
  14. 2020OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open Worldcited by 93
  15. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  16. 2021Novel Class Discovery in Semantic Segmentationcited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 16; 2024: 9; 2025: 10; 2026: 5.

42 papers.

Sort:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
  3. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
  4. 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 90
  5. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  6. 2023MetaGCD: Learning to Continually Learn in Generalized Category Discoverycited by 40
  7. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  8. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  9. 2023CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discoverycited by 26
  10. 2023Federated Generalized Category Discoverycited by 26
  11. 2023Incremental Generalized Category Discoverycited by 25
  12. 2024Democratizing Fine-grained Visual Recognition with Large Language Modelscited by 25
30 more
  1. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  2. 2022Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalizationcited by 22
  3. 2023Novel Class Discovery for 3D Point Cloud Semantic Segmentationcited by 21
  4. 2025ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discoverycited by 19
  5. 2024Happy: A Debiased Learning Framework for Continual Generalized Category Discoverycited by 18
  6. 2023Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discoverycited by 16
  7. 2024Effective Prompt Pool Learning for Continual Category Discoverycited by 14
  8. 2023Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discoverycited by 11
  9. 2023Category Adaptation Meets Projected Distillation in Generalized Continual Category Discoverycited by 5
  10. 2024Online Continuous Generalized Category Discoverycited by 5
  11. 2024Deep Active Learning in the Open Worldcited by 5
  12. 2025Category Discovery: An Open-World Perspectivecited by 5
  13. 2023Novel class discovery meets foundation models for 3D semantic segmentationcited by 4
  14. 2023Federated Continual Novel Class Learningcited by 4
  15. 2024Continual Novel Class Discovery via Feature Enhancement and Adaptationcited by 2
  16. 2025Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Expertscited by 2
  17. 2024Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learningcited by 1
  18. 2025Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learningcited by 1
  19. 2026TALON: Test-time Adaptive Learning for On-the-Fly Category Discoverycited by 1
  20. 2024YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discoverycited by 0
  21. 2025Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discoverycited by 0
  22. 2025Few-shot Novel Category Discoverycited by 0
  23. 2025Interpretable Text-Guided Image Clustering via Iterative Searchcited by 0
  24. 2025Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discoverycited by 0
  25. 2025Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labelscited by 0
  26. 2025Learning After Model Deploymentcited by 0
  27. 2026SIEFormer: Spectral-Interpretable and -Enhanced Transformer for Generalized Category Discoverycited by 0
  28. 2026Virtual Category-Guided Continual Generalized Category Discoverycited by 0
  29. 2026Fourier Self-Supervision for Fine-Grained Generalized Category Discoverycited by 0
  30. 2026Generalized Biomedicine Discoverycited by 0