AI Paper Atlas

Research map / Continual learning / Online and replay-based

PromptFusion: Decoupling Stability and Plasticity for Continual Learning

Haoran Chen, Zuxuan Wu, Xintong Han, Menglin Jia, Yu-Gang Jiang

ECCV 2024 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 23 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 the weight mask W balancing old and new classes (ablation)PromptFusion · Split-CIFAR100average accuracy: 84.2 -> 88.5Improved
add learnable fusion weight lambda instead of simple summation (ablation)PromptFusion · Split-CIFAR100average accuracy: 87.4 -> 88.5Improved
add image prompts to augment CoOp (ablation)PromptFusion · Split-CIFAR100average accuracy: 87.1 -> 88.5Improved
add usage penalty term to PromptFusion-Lite (ablation)PromptFusion-Lite · Split-CIFAR100GFLOPs: 42.6 -> 38.3 GFLOPs; Acc 88.2 -> 87.3Improved
add knowledge distillation on the decision module F (ablation)PromptFusion-Lite · Split-CIFAR100average accuracy: 87.0 -> 87.3Improved
use PromptFusion with Stabilizer (CoOp) and Booster (VPT) instead of prompt-pool methodsL2P, DualPrompt, CODA-Prompt · Split-ImageNet-R memory-freeaverage accuracy: 78.7, +5.3 over CODA-PromptImproved
use CoOp (Stabilizer) in place of VPT for retaining old tasksprompt tuning for continual learning · Split-CIFAR100 pilotaverage performance drop on old tasks: VPT 23.0% -> CoOp 9.9%Improved
train a new VPT prompt set per task and concatenate (ablation)Booster module · Split-CIFAR100average accuracyHurt
swap ViT backbone weights for CLIP visual encoder in VPT (ablation)VPT · Split-CIFAR100 pilotaverage accuracyHurt
use PromptFusion-Lite instead of PromptFusionPromptFusion · Split-ImageNet-Raccuracy and GFLOPs: Acc 82.2 -> 81.5; GFLOPs 42.6 -> 34.4Mixed
vary memory buffer size from 1K to 5K (ablation)PromptFusion · Split-CIFAR100, Split-ImageNet-R, Core50average accuracyNo clear effect

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