AI Paper Atlas

Research map / Continual learning / Online and replay-based

One-stage Prompt-based Continual Learning

Youngeun Kim, Yuhang Li, Priyadarshini Panda

ECCV 2024 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 16 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 Query-Pool Regularization loss with cosine similarity and softmax (ablation)OS-Prompt · ImageNet-R 10-taskAverage final accuracy A_N (%): 75.00 -> 75.67Improved
use intermediate token embedding as prompt query (one-stage) instead of separate query ViT (ablation)CodaPrompt-style PCL · ImageNet-R 5/10/20-taskAverage final accuracy A_N (%): 75.45 -> 74.58 (10-task, with CodaPrompt formation)Hurt
apply one-stage framework to L2P prompt formation (ablation)Deep L2P · ImageNet-R 10-taskAverage final accuracy A_N (%): 71.66 -> 73.43Improved
apply one-stage framework to DualPrompt formation (ablation)DualPrompt · ImageNet-R 10-taskAverage final accuracy A_N (%): 71.32 -> 72.57Improved
remove query ViT at inference (one-stage)OS-Prompt · ViT-B/16 inferenceGFLOPs relative to prior PCL (%): 100 -> 50.1Improved
use one-stage design for trainingOS-Prompt · relative training complexity vs ERRelative training cost: 1 -> 2/3Improved
use unsupervised DINO pretrained weights instead of supervised ImageNet-1kPCL methods · ImageNet-R 10-taskAverage final accuracy A_N (%): 75.45 -> 67.61 (CodaPrompt)Hurt
vary QR loss weight lambda from 1e-5 to 5e-4 (ablation)OS-Prompt++ · ImageNet-R 5/10/20-taskAverage final accuracy A_N (%): 75.63 -> 75.68 (10-task)No clear effect
use CodaPrompt soft-matching formation in one-stage framework (ablation)OS-Prompt · ImageNet-R 10-taskAverage final accuracy A_N (%): 75.45 -> 74.58Hurt
add QR loss to OS-Prompt for DomainNet (ablation)OS-Prompt · DomainNet 5-taskAverage final accuracy A_N (%): 72.24 -> 73.32Improved

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