# MetaGCD: Learning to Continually Learn in Generalized Category Discovery

arXiv: https://arxiv.org/abs/2308.11063 · HTML: https://mlsanity.com/paper/2308.11063/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 56 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Builds on (most cited first, 30 of 40)

- [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)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Mnemonics Training: Multi-Class Incremental Learning without Forgetting](https://mlsanity.com/paper/2002.10211/) (2020)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Adaptive Risk Minimization: Learning to Adapt to Domain Shift](https://mlsanity.com/paper/2007.02931/) (2020)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples](https://mlsanity.com/paper/2103.05905/) (2021)
- [Automatically Discovering and Learning New Visual Categories with Ranking Statistics](https://mlsanity.com/paper/2002.05714/) (2020)
- [Neighborhood Contrastive Learning for Novel Class Discovery](https://mlsanity.com/paper/2106.10731/) (2021)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [AutoNovel: Automatically Discovering and Learning Novel Visual Categories](https://mlsanity.com/paper/2106.15252/) (2021)
- [Improved Few-Shot Visual Classification](https://mlsanity.com/paper/1912.03432/) (2019)
- [Self-Supervised Generalisation with Meta Auxiliary Learning](https://mlsanity.com/paper/1901.08933/) (2019)
- [Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay](https://mlsanity.com/paper/2207.11213/) (2022)
- [Few-shot Scene-adaptive Anomaly Detection](https://mlsanity.com/paper/2007.07843/) (2020)

## Built on by (most cited first, 30 of 42)

- [Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery](https://mlsanity.com/paper/2310.19776/) (2023)
- [Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization](https://mlsanity.com/paper/2312.10165/) (2023)
- [Adapting to Distribution Shift by Visual Domain Prompt Generation](https://mlsanity.com/paper/2405.02797/) (2024)
- [Happy: A Debiased Learning Framework for Continual Generalized Category Discovery](https://mlsanity.com/paper/2410.06535/) (2024)
- [Effective Prompt Pool Learning for Continual Category Discovery](https://mlsanity.com/paper/2407.19001/) (2024)
- [Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2506.17307/) (2025)
- [Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams](https://mlsanity.com/paper/2407.12128/) (2024)
- [How to Train the Teacher Model for Effective Knowledge Distillation](https://mlsanity.com/paper/2407.18041/) (2024)
- [Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2508.20265/) (2025)
- [MOS: Modeling Object-Scene Associations in Generalized Category Discovery](https://mlsanity.com/paper/2503.12035/) (2025)
- [Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery](https://mlsanity.com/paper/2507.04051/) (2025)
- [Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs](https://mlsanity.com/paper/2512.19918/) (2025)
- [Towards Incremental Learning in Large Language Models: A Critical Review](https://mlsanity.com/paper/2404.18311/) (2024)
- [ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imaging](https://mlsanity.com/paper/2603.06658/) (2026)
- [Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery](https://mlsanity.com/paper/2308.12112/) (2023)
- [Online Continuous Generalized Category Discovery](https://mlsanity.com/paper/2408.13492/) (2024)
- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [Generalized Category Discovery in Semantic Segmentation](https://mlsanity.com/paper/2311.11525/) (2023)
- [Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery](https://mlsanity.com/paper/2404.08995/) (2024)
- [DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning](https://mlsanity.com/paper/2501.12898/) (2025)
- [Continual Novel Class Discovery via Feature Enhancement and Adaptation](https://mlsanity.com/paper/2405.06389/) (2024)
- [A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization](https://mlsanity.com/paper/2410.21807/) (2024)
- [MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning](https://mlsanity.com/paper/2505.20513/) (2025)
- [Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning](https://mlsanity.com/paper/2408.10046/) (2024)
- [Proxy-Anchor and EVT-Driven Continual Learning Method for Generalized Category Discovery](https://mlsanity.com/paper/2504.08550/) (2025)
- [GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery](https://mlsanity.com/paper/2602.19872/) (2026)
- [TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery](https://mlsanity.com/paper/2603.08075/) (2026)
- [Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation](https://mlsanity.com/paper/2410.13094/) (2024)
- [Towards Robust Incremental Learning under Ambiguous Supervision](https://mlsanity.com/paper/2501.13584/) (2025)
- [Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discovery](https://mlsanity.com/paper/2503.09106/) (2025)

## Abstract (arXiv)

In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while maintaining the performance in known classes. We name the setting Continual Generalized Category Discovery (C-GCD). Existing methods for novel class discovery cannot directly handle the C-GCD setting due to some unrealistic assumptions, such as the unlabeled data only containing novel classes. Furthermore, they fail to discover novel classes in a continual fashion. In this work, we lift all these assumptions and propose an approach, called MetaGCD, to learn how to incrementally discover with less forgetting. Our proposed method uses a meta-learning framework and leverages the offline labeled data to simulate the testing incremental learning process. A meta-objective is defined to revolve around two conflicting learning objectives to achieve novel class discovery without forgetting. Furthermore, a soft neighborhood-based contrastive network is proposed to discriminate uncorrelated images while attracting correlated images. We build strong baselines and conduct extensive experiments on three widely used benchmarks to demonstrate the superiority of our method.