AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning

Kiseong Hong, Gyeong-hyeon Kim, Eunwoo Kim

ICCV 2025 · Continual learning › Domain and prompt-based · approach: Prompt-based continual learning · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
add task-conditioning step (TC) (ablation)RainbowPrompt · ImageNet-R 10-taskaverage accuracy: 78.92 -> 79.09Improved
add task-conditioning step (TC) (ablation)RainbowPrompt · ImageNet-R 10-taskforgetting: 4.19 -> 3.90Improved
add task-level transformation (TLT) (ablation)RainbowPrompt · ImageNet-R 10-taskaverage accuracy: 78.70 -> 79.09Improved
add task-level transformation (TLT) (ablation)RainbowPrompt · ImageNet-R 10-taskforgetting: 4.14 -> 3.90Improved
add feature-level transformation (FLT) (ablation)RainbowPrompt · ImageNet-R 10-taskaverage accuracy: 78.57 -> 79.09Improved
add feature-level transformation (FLT) (ablation)RainbowPrompt · ImageNet-R 10-taskforgetting: 4.29 -> 3.90Improved
add task-guided alignment (TGA) (ablation)RainbowPrompt · ImageNet-R 10-taskaverage accuracy: 66.31 -> 79.09Improved
add task-guided alignment (TGA) (ablation)RainbowPrompt · ImageNet-R 10-taskforgetting: 4.84 -> 3.90Improved
use adaptive prompting (learned gate) instead of manual prompting (ablation)RainbowPrompt · ImageNet-R 10-taskaverage accuracy: 78.13 -> 79.09Improved
use adaptive prompting instead of manual prompting (ablation)RainbowPrompt · ImageNet-R 10-taskaccuracy gain over manual prompting: 1.98% accuracy gain and 0.26% less forgettingImproved
use adaptive prompting instead of manual prompting (ablation)RainbowPrompt · CUBS 10-taskaverage accuracy: 3.61% higher average accuracy and 2.34% lower forgettingImproved
use adaptive prompting instead of manual prompting (ablation)RainbowPrompt · ImageNet-R 10-taskforgetting: 4.07 -> 3.90Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy