# Virtual Category-Guided Continual Generalized Category Discovery

arXiv: https://arxiv.org/abs/2607.04984 · HTML: https://mlsanity.com/paper/2607.04984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Neighborhood Contrastive Learning for Novel Class Discovery](https://mlsanity.com/paper/2106.10731/) (2021)
- [Parametric Classification for Generalized Category Discovery: A Baseline Study](https://mlsanity.com/paper/2211.11727/) (2022)
- [Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data](https://mlsanity.com/paper/2104.12673/) (2021)
- [Class-incremental Novel Class Discovery](https://mlsanity.com/paper/2207.08605/) (2022)
- [MetaGCD: Learning to Continually Learn in Generalized Category Discovery](https://mlsanity.com/paper/2308.11063/) (2023)
- [Parametric Information Maximization for Generalized Category Discovery](https://mlsanity.com/paper/2212.00334/) (2022)
- [OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2207.02261/) (2022)
- [Generalized Category Discovery with Decoupled Prototypical Network](https://mlsanity.com/paper/2211.15115/) (2022)
- [Grow and Merge: A Unified Framework for Continuous Categories Discovery](https://mlsanity.com/paper/2210.04174/) (2022)
- [Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier](https://mlsanity.com/paper/2211.11262/) (2022)
- [Happy: A Debiased Learning Framework for Continual Generalized Category Discovery](https://mlsanity.com/paper/2410.06535/) (2024)
- [Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels](https://mlsanity.com/paper/2312.01169/) (2023)
- [ImbaGCD: Imbalanced Generalized Category Discovery](https://mlsanity.com/paper/2401.05353/) (2023)
- [Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay](https://mlsanity.com/paper/2505.20049/) (2025)

## Abstract (arXiv)

Continual Generalized Category Discovery (C-GCD) aims to incrementally identify novel categories from sequential unlabeled data while preserving recognition of known classes, which is an essential capability for open-world visual learning. A major bottleneck lies in ambiguous unlabeled samples that cannot be confidently assigned to known classes nor reliably grouped as novel ones, making pseudo-labeling brittle and often biasing learning toward familiar categories. In this work, we introduce Virtual Category-Guided Continual Generalized Category Discovery by adapting Virtual Category Learning (VCL) to the continual setting. Our method identifies uncertain samples and assigns them to temporary virtual categories, enabling safe and informative learning from unlabeled streams without injecting noisy labels, while improving unlabeled data utilization and mitigating prediction bias. To further stabilize discovery across sessions and enhance class separation, we augment VCL with Expanded Neighborhood Contrastive Learning (ENCL), which exploits extended neighborhood relations and an adaptive margin to learn more discriminative and well-separated representations for both old and emerging classes. Extensive experiments on CIFAR-100, Tiny ImageNet, and ImageNet-100 demonstrate that our approach consistently outperforms state-of-the-art methods, establishing a scalable and effective solution for C-GCD.