mlsanityData to 7 Oct 2026

Online Continuous Generalized Category Discovery

arXiv 2408.13492 ↗First posted 24 Aug 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

With the advancement of deep neural networks in computer vision, artificial intelligence (AI) is widely employed in real-world applications. However, AI still faces limitations in mimicking high-level human capabilities, such as novel category discovery, for practical use. While some methods utilizing offline continual learning have been proposed for novel category discovery, they neglect the continuity of data streams in real-world settings. In this work, we introduce Online Continuous Generalized Category Discovery (OCGCD), which considers the dynamic nature of data streams where data can be created and deleted in real time. Additionally, we propose a novel method, DEAN, Discovery via Energy guidance and feature AugmentatioN, which can discover novel categories in an online manner through energy-guided discovery and facilitate discriminative learning via energy-based contrastive loss. Furthermore, DEAN effectively pseudo-labels unlabeled data through variance-based feature augmentation. Experimental results demonstrate that our proposed DEAN achieves outstanding performance in proposed OCGCD scenario.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 24 Aug 2024.

Builds on

35 of 47 references.

References · 35

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2020Supervised Contrastive Learningcited by 2,803
  6. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  8. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 714
  9. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  10. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 376
  11. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  12. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
23 more
  1. 2022Generalized Category Discoverycited by 209
  2. 2021A Unified Objective for Novel Class Discoverycited by 161
  3. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
  4. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  5. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  6. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  7. 2019Multi-class Classification without Multi-class Labelscited by 100
  8. 2020OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open Worldcited by 93
  9. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  10. 2020Incremental Learning In Online Scenariocited by 71
  11. 2021Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inferencecited by 66
  12. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  13. 2022Class-incremental Novel Class Discoverycited by 42
  14. 2023MetaGCD: Learning to Continually Learn in Generalized Category Discoverycited by 40
  15. 2022Novel Class Discovery without Forgettingcited by 39
  16. 2023Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuningcited by 35
  17. 2024Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learnerscited by 35
  18. 2022Grow and Merge: A Unified Framework for Continuous Categories Discoverycited by 33
  19. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  20. 2024Generative Unlearning for Any Identitycited by 19
  21. 2023Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discoverycited by 16
  22. 2024Open-Set Domain Adaptation for Semantic Segmentationcited by 13
  23. 2022SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labelscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Consistent Supervised-Unsupervised Alignment for Generalized Category Discoverycited by 5
  2. 2025Category Discovery: An Open-World Perspectivecited by 5
  3. 2026Detecting Unknown Objects via Energy-based Separation for Open World Object Detectioncited by 2
  4. 2025ReLKD: Inter-Class Relation Learning with Knowledge Distillation for Generalized Category Discoverycited by 0
  5. 2026Rondo: Unsupervised Discovery of Recurring Temporal Structurecited by 0