Research map / Continual learning / Class-incremental
Learning a Fix and Explore Framework for Continuous Generalized Category Discovery
Chunming Li, Shidong Wang, Haofeng Zhang
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 |
|---|---|---|---|
| FaE vs Happy at Stage-5 | C-GCD · CIFAR-100 | ACC (All): 59.99 -> 65.20 | Improved |
| FaE vs Happy at Stage-5 | C-GCD · Tiny-ImageNet | ACC (All): 54.56 -> 63.65 | Improved |
| FaE vs Happy at Stage-1 | C-GCD · CUB-200 | ACC (All): 81.40 -> 80.80 | Hurt |
| FaE vs Happy maximum forgetting | C-GCD · CIFAR-100 | Mf: 11.22 -> 6.82 | Improved |
| add graph regularization (full FaE vs distill-only) (ablation) | FaE · CIFAR-100 | ACC (All): 72.44 -> 73.34 | Improved |
| graph distill on new + cosine distill on old instead of cosine for both (ablation) | FaE · Tiny-ImageNet | ACC (All): 65.58 -> 70.35 | Improved |
| cosine on old and graph on new vs graph for both (ablation) | FaE · CIFAR-100 | ACC (All): 69.95 -> 72.44 | Improved |
| extend to 10 stages vs Happy | C-GCD · Tiny-ImageNet | ACC (All) at Stage-10: 50.69 -> 61.83 | Improved |
Closest papers by meaning
- Happy: A Debiased Learning Framework for Continual Generalized Category Discovery (NeurIPS 2024 · similarity 0.92)
- Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective (ICML 2025 · similarity 0.92)
- Solving the Catastrophic Forgetting Problem in Generalized Category Discovery (CVPR 2024 · similarity 0.90)
- Transfer and Alignment Network for Generalized Category Discovery (AAAI 2024 · similarity 0.90)
- Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery (NeurIPS 2025 · similarity 0.89)
- A Unified Knowledge Transfer Network for Generalized Category Discovery (AAAI 2024 · similarity 0.89)
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.
