Research map / Continual learning / Domain and prompt-based
RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning
Kiseong Hong, Gyeong-hyeon Kim, Eunwoo Kim
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 task-conditioning step (TC) (ablation) | RainbowPrompt · ImageNet-R 10-task | average accuracy: 78.92 -> 79.09 | Improved |
| add task-conditioning step (TC) (ablation) | RainbowPrompt · ImageNet-R 10-task | forgetting: 4.19 -> 3.90 | Improved |
| add task-level transformation (TLT) (ablation) | RainbowPrompt · ImageNet-R 10-task | average accuracy: 78.70 -> 79.09 | Improved |
| add task-level transformation (TLT) (ablation) | RainbowPrompt · ImageNet-R 10-task | forgetting: 4.14 -> 3.90 | Improved |
| add feature-level transformation (FLT) (ablation) | RainbowPrompt · ImageNet-R 10-task | average accuracy: 78.57 -> 79.09 | Improved |
| add feature-level transformation (FLT) (ablation) | RainbowPrompt · ImageNet-R 10-task | forgetting: 4.29 -> 3.90 | Improved |
| add task-guided alignment (TGA) (ablation) | RainbowPrompt · ImageNet-R 10-task | average accuracy: 66.31 -> 79.09 | Improved |
| add task-guided alignment (TGA) (ablation) | RainbowPrompt · ImageNet-R 10-task | forgetting: 4.84 -> 3.90 | Improved |
| use adaptive prompting (learned gate) instead of manual prompting (ablation) | RainbowPrompt · ImageNet-R 10-task | average accuracy: 78.13 -> 79.09 | Improved |
| use adaptive prompting instead of manual prompting (ablation) | RainbowPrompt · ImageNet-R 10-task | accuracy gain over manual prompting: 1.98% accuracy gain and 0.26% less forgetting | Improved |
| use adaptive prompting instead of manual prompting (ablation) | RainbowPrompt · CUBS 10-task | average accuracy: 3.61% higher average accuracy and 2.34% lower forgetting | Improved |
| use adaptive prompting instead of manual prompting (ablation) | RainbowPrompt · ImageNet-R 10-task | forgetting: 4.07 -> 3.90 | Improved |
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.
- DualPrompt — DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning (ECCV 2022) · better on 4 of 4 shared results
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
- Evolving Parameterized Prompt Memory for Continual Learning (AAAI 2024 · similarity 0.91)
- Convolutional Prompting meets Language Models for Continual Learning (CVPR 2024 · similarity 0.89)
- REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning (NeurIPS 2025 · similarity 0.89)
- Vector Quantization Prompting for Continual Learning (NeurIPS 2024 · similarity 0.88)
- Consistent Prompting for Rehearsal-Free Continual Learning (CVPR 2024 · similarity 0.88)
- Training Consistent Mixture-of-Experts-Based Prompt Generator for Continual Learning (AAAI 2025 · similarity 0.88)
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.
