AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

Non-Exemplar Domain Incremental Learning via Cross-Domain Concept Integration

Qiang Wang, Yuhang He, Songlin Dong, Xinyuan Gao, Shaokun Wang, Yihong Gong

ECCV 2024 · Continual learning › Domain and prompt-based · approach: Domain-incremental learning with memory · 13 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 a unified classifier plus domain alignment instead of extending classifiers per domain (ablation)NEDIL on ViT · DomainNet DILaverage accuracy AT: 50.62 -> 61.58 (baseline vs UC+DSA with K-NN)Improved
Add Patch Shuffle Selector instead of K-NN domain selector (ablation)UC+DSA · DomainNet DILaverage accuracy AT: 61.58 -> 62.23Improved
Add Patch Shuffle Selector instead of NMC (ablation)UC+DSA · CORe50 DILaverage accuracy AT: 89.15 -> 90.01Improved
Add PSS to the S-Prompts baseline (without UC+DSA) (ablation)S-Prompts baseline · DomainNet DILaverage accuracy AT: 50.62 -> 51.29Improved
Use CLIP backbone with PINA instead of beating MoP-CLIP on CORe50PINA-D (CLIP) · CORe50 DILaverage accuracy AT: 89.23 vs 92.29 (MoP-CLIP)Hurt
Use lowest-quality domain (quickdraw) as the base domain instead of real (ablation)PINA-D · DomainNet DILaverage accuracy AT: 66.67 -> 56.52Hurt
Use deep branch alignment (PINA-D) instead of shallow branch at same parameter count (ablation)DSA module · DomainNet DILaverage accuracy AT: +3.2%Improved
Increase prompt token length to 10 or more (ablation)PINA · DomainNet DILaverage accuracy ATImproved
Use PINA instead of S-iPrompts at fewer parametersNEDIL on ViT · DomainNet DILaverage accuracy AT: 50.62 -> 54.86 with 0.6 vs 1.8 extra parametersImproved

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