Research map / Label-efficient and robust learning / Recognition and long-tail
Grow and Merge: A Unified Framework for Continuous Categories Discovery
Xinwei Zhang, Jianwen Jiang, Yutong Feng, Zhi-Fan Wu, Xibin Zhao, Hai Wan, Mingqian Tang, Rong Jin, Yue Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Separate novel-category discovery and known-category maintenance into growing and merging phases | Grow and Merge (GM) · Continuous Category Discovery, four scenarios | performance | Improved |
| Use average distance of the top-j nearest neighbors instead of maximum distance (ablation) | GM sample sifting · Continuous Category Discovery | performance | Hurt |
| Set the novelty-detection threshold to 0.6 (ablation) | GM · Continuous Category Discovery | performance | Improved |
| Vary the novelty-detection threshold within [0.4, 0.7] rather than using 0.6 (ablation) | GM · Continuous Category Discovery | performance | No clear effect |
Closest papers by meaning
- PRISM: Progressive Robust Learning for Open-World Continual Category Discovery (ICLR 2026 · similarity 0.90)
- Beyond the Static World: Continual Category Discovery under Visual Drift (CVPR 2026 · similarity 0.89)
- Happy: A Debiased Learning Framework for Continual Generalized Category Discovery (NeurIPS 2024 · similarity 0.87)
- Semantic-Guided Novel Category Discovery (AAAI 2024 · similarity 0.87)
- Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery (AAAI 2025 · similarity 0.86)
- Adaptive Discovering and Merging for Incremental Novel Class Discovery (AAAI 2024 · similarity 0.86)
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.
