Research map / Continual learning / Class-incremental
Online Continuous Generalized Category Discovery
Keon-Hee Park, Hakyung Lee, Kyungwoo Song, Gyeong-Moon Park
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 |
|---|---|---|---|
| add LoRA parameter-efficient tuning (ablation) | fine-tuning baseline · CUB200 (OCGCD) | forgetting F: 80.52 -> 22.24 | Improved |
| add energy-guided discovery (ablation) | baseline + LoRA · CUB200 (OCGCD) | M_new: 6.24 -> 23.67 | Improved |
| add energy-based contrastive loss (ablation) | baseline + LoRA + EGD · CUB200 (OCGCD) | M_all: 54.97 -> 57.37 | Improved |
| add variance-based feature augmentation (ablation) | DEAN · CUB200 (OCGCD) | M_new: 27.63 -> 33.11 | Improved |
| add VFA with K=5 augmented vectors (ablation) | DEAN · CUB200 pseudo-labels | M_new^PS: 46.47 -> 65.75 | Improved |
| increase K above 5 in VFA (ablation) | DEAN · CUB200 pseudo-labels | M_all^PS: 76.93 -> 75.44 (K=7), 75.22 (K=9) | Hurt |
| use energy-guided discovery instead of CGCD fine-split (ablation) | DEAN · CIFAR-100 (OCGCD) | M_all: 52.27 -> 62.34 | Improved |
| use LoRA instead of Adapter or Prefix (ablation) | DEAN · CUB200 (OCGCD) | M_all: 56.96 (Adapter), 58.54 (Prefix) -> 59.56 | Improved |
| DEAN versus CGCD pseudo-label quality | DEAN · CUB200 pseudo-labels | M_all^PS: 61.88 -> 76.93 | Improved |
| add energy-based contrastive loss without VFA (ablation) | DEAN w/o VFA · CUB200 pseudo-labels | M_new^PS: 45.80 -> 46.47 | No clear effect |
Closest papers by meaning
- Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective (ICML 2025 · similarity 0.87)
- Happy: A Debiased Learning Framework for Continual Generalized Category Discovery (NeurIPS 2024 · similarity 0.87)
- Solving the Catastrophic Forgetting Problem in Generalized Category Discovery (CVPR 2024 · similarity 0.86)
- Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery (NeurIPS 2025 · similarity 0.86)
- Active Generalized Category Discovery (CVPR 2024 · similarity 0.86)
- Towards Understanding Parametric Generalized Category Discovery on Graphs (ICML 2025 · 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.
