# Generalized Category Discovery with Decoupled Prototypical Network

arXiv: https://arxiv.org/abs/2211.15115 · HTML: https://mlsanity.com/paper/2211.15115/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 28 Nov 2022.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)
- [Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.16765/) (2021)
- [Discovering New Intents with Deep Aligned Clustering](https://mlsanity.com/paper/2012.08987/) (2020)
- [Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement](https://mlsanity.com/paper/1911.08891/) (2019)
- [Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning](https://mlsanity.com/paper/2109.06349/) (2021)
- [New Intent Discovery with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2205.12914/) (2022)
- [TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition](https://mlsanity.com/paper/2110.15063/) (2021)
- [Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning](https://mlsanity.com/paper/2210.07733/) (2022)
- [Automatic Discovery of Novel Intents & Domains from Text Utterances](https://mlsanity.com/paper/2006.01208/) (2020)

## Built on by (most cited first, 30 of 35)

- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [No Representation Rules Them All in Category Discovery](https://mlsanity.com/paper/2311.17055/) (2023)
- [Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery](https://mlsanity.com/paper/2310.19776/) (2023)
- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [Solving the Catastrophic Forgetting Problem in Generalized Category Discovery](https://mlsanity.com/paper/2501.05272/) (2025)
- [HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts](https://mlsanity.com/paper/2408.04591/) (2024)
- [Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery](https://mlsanity.com/paper/2410.19213/) (2024)
- [Generalized Category Discovery with Large Language Models in the Loop](https://mlsanity.com/paper/2312.10897/) (2023)
- [Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling](https://mlsanity.com/paper/2403.01053/) (2024)
- [Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery](https://mlsanity.com/paper/2507.04051/) (2025)
- [Context-Aware Clustering using Large Language Models](https://mlsanity.com/paper/2405.00988/) (2024)
- [Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery](https://mlsanity.com/paper/2409.19659/) (2024)
- [A Diffusion Weighted Graph Framework for New Intent Discovery](https://mlsanity.com/paper/2310.15836/) (2023)
- [Transfer and Alignment Network for Generalized Category Discovery](https://mlsanity.com/paper/2312.16467/) (2023)
- [Multimodal Generalized Category Discovery](https://mlsanity.com/paper/2409.11624/) (2024)
- [New Intent Discovery with Attracting and Dispersing Prototype](https://mlsanity.com/paper/2403.16913/) (2024)
- [A Survey of Ontology Expansion for Conversational Understanding](https://mlsanity.com/paper/2410.15019/) (2024)
- [GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback](https://mlsanity.com/paper/2502.18414/) (2025)
- [A Generic Method for Fine-grained Category Discovery in Natural Language Texts](https://mlsanity.com/paper/2406.13103/) (2024)
- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [DNA: Denoised Neighborhood Aggregation for Fine-grained Category Discovery](https://mlsanity.com/paper/2310.10151/) (2023)
- [Generalized Category Discovery with Clustering Assignment Consistency](https://mlsanity.com/paper/2310.19210/) (2023)
- [Federated Continual Novel Class Learning](https://mlsanity.com/paper/2312.13500/) (2023)
- [Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery](https://mlsanity.com/paper/2404.08995/) (2024)
- [Exploration and Exploitation of Unlabeled Data for Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2306.17699/) (2023)
- [RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations](https://mlsanity.com/paper/2404.08977/) (2024)
- [Towards Real-world Scenario: Imbalanced New Intent Discovery](https://mlsanity.com/paper/2406.03127/) (2024)
- [One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning](https://mlsanity.com/paper/2407.09011/) (2024)
- [Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery](https://mlsanity.com/paper/2410.20219/) (2024)
- [Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs](https://mlsanity.com/paper/2505.23304/) (2025)

## Abstract (arXiv)

Generalized Category Discovery (GCD) aims to recognize both known and novel categories from a set of unlabeled data, based on another dataset labeled with only known categories. Without considering differences between known and novel categories, current methods learn about them in a coupled manner, which can hurt model's generalization and discriminative ability. Furthermore, the coupled training approach prevents these models transferring category-specific knowledge explicitly from labeled data to unlabeled data, which can lose high-level semantic information and impair model performance. To mitigate above limitations, we present a novel model called Decoupled Prototypical Network (DPN). By formulating a bipartite matching problem for category prototypes, DPN can not only decouple known and novel categories to achieve different training targets effectively, but also align known categories in labeled and unlabeled data to transfer category-specific knowledge explicitly and capture high-level semantics. Furthermore, DPN can learn more discriminative features for both known and novel categories through our proposed Semantic-aware Prototypical Learning (SPL). Besides capturing meaningful semantic information, SPL can also alleviate the noise of hard pseudo labels through semantic-weighted soft assignment. Extensive experiments show that DPN outperforms state-of-the-art models by a large margin on all evaluation metrics across multiple benchmark datasets. Code and data are available at https://github.com/Lackel/DPN.