Research map / Continual learning / Class-incremental
Class-Domain Incremental Learning with Extensible Multi-Center Modeling
Xuetong Yang, Yuxiang Yan, Zhiyuan Zhou, Xin Gao, Guanghao Li, Jian Pu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes EMCift, a class-domain incremental learning method using extensible multi-center modeling with dual-path drift harmonization to handle simultaneous expansion of class and domain spaces.
Problem
Incremental learning when both class and domain spaces expand simultaneously, causing catastrophic forgetting from fragmented data streams.
Approach
Extensible multi-center modeling of class-domain pairs combined with dual-path drift harmonization to stabilize continual learning as both classes and domains grow.
Closest papers by meaning
- Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning (ICLR 2026 · similarity 0.90)
- Striking a Balance Between Stability and Plasticity for Class-Incremental Learning (ICCV 2021 · similarity 0.89)
- Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning (CVPR 2025 · similarity 0.87)
- Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning (ICML 2025 · similarity 0.87)
- Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning (ICML 2024 · similarity 0.87)
- Long-Tail Class Incremental Learning via Independent Sub-prototype Construction (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
