AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning

Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi, Ruoxi Sun, Han Zhang, Chen-Yu Lee, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, Tomas Pfister

ECCV 2022 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 616 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
use Prefix Tuning instead of Prompt Tuning (ablation)DualPrompt · Split CIFAR-100average accuracy: 83.81 -> 86.51Improved
use Prefix Tuning instead of Prompt Tuning (ablation)DualPrompt · Split ImageNet-Raverage accuracy: 64.99 -> 68.13Improved
add G-Prompt alone to frozen backbone (ablation)DualPrompt · Split ImageNet-Raverage accuracy: 27.01 -> 63.41Improved
add E-Prompt alone to frozen backbone (ablation)DualPrompt · Split ImageNet-Raverage accuracy: 27.01 -> 65.10Improved
add G-Prompt to E-Prompt (ablation)DualPrompt · Split ImageNet-Raverage accuracy: 65.10 -> 66.77Improved
add E-Prompt to G-Prompt (ablation)DualPrompt · Split ImageNet-Rforgetting: 6.52 -> 5.74Improved
extend G- and E-Prompt to multiple layers (ablation)DualPrompt · Split ImageNet-Raverage accuracy: 66.77 -> 68.13Improved
extend G-Prompt alone to multiple layers (ablation)DualPrompt G-Prompt only · Split ImageNet-Rforgetting: 63.41 -> 63.85Mixed
attach G-Prompt to layers 1-12 instead of 1-2 (ablation)DualPrompt · Split ImageNet-R (validation)average accuracy: 68.46 -> 63.13Hurt
use ground-truth task identity to select E-Prompt (ablation)DualPrompt · Split ImageNet-Raverage accuracy: 68.13 -> 71.97Improved
replace L2P with DualPromptDualPrompt · Split ImageNet-Rforgetting: 9.73 -> 4.68Improved
replace L2P with DualPromptDualPrompt · Split CIFAR-100average accuracy: 83.86 -> 86.51Improved

Later papers that compared with this method

50 later accepted papers report DualPrompt as a baseline in their results tables; 49 of them report a better number on most of the results they share with it.

42 more not listed.

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