paper-with-me

Papers

Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition

2023-10-16 · Xiaoshuai Song, Yutao Mou, Keqing He, Yueyan Qiu, Pei Wang, Weiran Xu

In a practical dialogue system, users may input out-of-domain (OOD) queries. The Generalized Intent Discovery (GID) task aims to discover OOD intents from OOD queries and extend them to the in-domain (IND) classifier. However, GID only considers one stage of OOD learning, and needs to utilize the data in all previous stages for joint training, which limits its wide application in reality. In this paper, we introduce a new task, Continual Generalized Intent Discovery (CGID), which aims to continuously and automatically discover OOD intents from dynamic OOD data streams and then incrementally add them to the classifier with almost no previous data, thus moving towards dynamic intent recognition in an open world. Next, we propose a method called Prototype-guided Learning with Replay and Distillation (PLRD) for CGID, which bootstraps new intent discovery through class prototypes and balances new and old intents through data replay and feature distillation. Finally, we conduct detailed experiments and analysis to verify the effectiveness of PLRD and understand the key challenges of CGID for future research.

📄 PDF Abstract BibTeX arXiv:2310.10184

Code (1)

songxiaoshuai/CGID 공식 구현 pytorch

Tasks

Intent DiscoveryIntent Recognition

Similar Papers 제목 키워드 기반

GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery

2026-02-23 · Jizhou Han, Chenhao Ding, SongLin Dong, Yuhang He 외 arxiv

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamical…

Novel Class Discovery

Virtual Category-Guided Continual Generalized Category Discovery

2026-07-06 · Jiahui Xiong, Qiuxia Lai, Hongsong Wang 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-wor…

Contrastive Learning

MetaGCD: Learning to Continually Learn in Generalized Category Discovery

2023-08-21 · ICCV 2023 1 · Yanan Wu, Zhixiang Chi, Yang Wang, Songhe Feng

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 …

Incremental LearningMeta-LearningNovel Class Discovery

PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery

2024-07-26 · Fernando Julio Cendra, Bingchen Zhao, Kai Han

We tackle the problem of Continual Category Discovery (CCD), which aims to automatically discover novel categories in a continuous stream of unlabeled data while mitigating the challenge of catastrophic forgetting -- an …

Continual LearningRepresentation Learning

Proxy-Anchor and EVT-Driven Continual Learning Method for Generalized Category Discovery

2025-04-11 · Alireza Fathalizadeh, Roozbeh Razavi-Far

Continual generalized category discovery has been introduced and studied in the literature as a method that aims to continuously discover and learn novel categories in incoming data batches while avoiding catastrophic fo…

Continual LearningKnowledge DistillationMetric Learning