Research map / Continual learning / Online and replay-based
PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery
Fernando Julio Cendra, Bingchen Zhao, Kai Han
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 Gaussian mixture prompts (top-k=5, 100 GMM samples) to GCD (ablation) | PromptCCD · CIFAR100 CCD | Avg. ACC All: 58.18 -> 64.17 | Improved |
| use top-k prompt selection instead of random-k prompts (ablation) | PromptCCD GMP · CIFAR100 CCD | Avg. ACC New: 55.68 -> 60.34 | Improved |
| use random-k prompts instead of no prompts (ablation) | PromptCCD · ImageNet-100 CCD | Avg. ACC All: 69.41 -> 68.30 | Hurt |
| use random-k prompts instead of no prompts (ablation) | PromptCCD · CUB CCD | Avg. ACC All: 54.98 -> 51.46 | Hurt |
| increase GMM samples from 100 to 200 (ablation) | PromptCCD GMP · CUB CCD | Avg. ACC All: 55.45 -> 51.67 | Hurt |
| use top-k 10 instead of 5 prompts (ablation) | PromptCCD GMP · CIFAR100 CCD | Avg. ACC All: 64.17 -> 61.03 | Hurt |
| add GMP plug-in to Grow & Merge (ablation) | Grow & Merge · CIFAR100 CCD | Avg. ACC All: 57.43 -> 61.14 | Improved |
| add GMP plug-in to MetaGCD (ablation) | MetaGCD · CIFAR100 CCD | Avg. ACC All: 55.49 -> 58.99 | Improved |
| vary prompt pool size from 5 to 200 for L2P and DualPrompt baselines (ablation) | PromptCCD-B · CUB CCD | All ACC: L2P 48.59 to 51.84; DP 53.97 to 55.54 | No clear effect |
| replace fixed-size prompt pool with Gaussian mixture pool | PromptCCD-B · CIFAR100 CCD | cACC All: 59.60 -> 63.97 | Improved |
| add replay to GCD | GCD · CIFAR100 CCD | cACC All: 58.18 -> 49.93 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MetaGCD — MetaGCD: Learning to Continually Learn in Generalized Category Discovery (ICCV 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Beyond the Static World: Continual Category Discovery under Visual Drift (CVPR 2026 · similarity 0.90)
- Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective (ICML 2025 · similarity 0.89)
- 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)
- SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning (ICLR 2024 · similarity 0.86)
- Convolutional Prompting meets Language Models for Continual Learning (CVPR 2024 · similarity 0.85)
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.
