AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

The Finer the Better: Towards Granular-aware Open-set Domain Generalization

Yunyun Wang, Zheng Duan, Xinyue Liao, Ke-Jia CHEN, Songcan Chen

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 1 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 semantic-aware prompt enhancement (SAPE) (ablation)CLIP baseline · OSDG ablationaccuracy and H-score: +6.93% accuracy, +16.36% H-scoreImproved
add semantic-guided diffusion generation (SGDG) (ablation)CLIP baseline · OSDG ablationaccuracy and H-score: +4.13% accuracy, +9.67% H-scoreImproved
add duplex contrastive learning (DCL) (ablation)CLIP baseline · OSDG ablationaccuracy and H-score: +5.54% accuracy, +13.30% H-scoreImproved
combine all three modules (SAPE, SGDG, DCL) (ablation)CLIP baseline · Office-Home OSDGH-score: 63.62 -> 98.97Improved
add alignment loss Lali (ablation)SeeCLIP · OSDG ablationaccuracy and H-score: -2.89% accuracy, -3.15% H-score when removedImproved
add repulsion loss Lrep (ablation)SeeCLIP · OSDG ablationaccuracy and H-score: -1.54% accuracy, -1.60% H-score when removedImproved
add cohesion loss Lcoh (ablation)SeeCLIP · OSDG ablationaccuracy and H-score: -0.64% accuracy, -0.65% H-score when removedImproved
add L1 regularization Lreg on semantic tokens (ablation)SeeCLIP · PACSaccuracy: 99.5 -> 99.9Improved
use semantic-guided diffusion instead of OpenGAN, Cumix or ODG-CLIP for pseudo-unknowns (ablation)SeeCLIP · Multi-Dataset OSDGaccuracy: 86.23 -> 88.70 vs ODG-CLIP generationImproved
prompt learning methods without explicit unknown handling (CoOp, CoCoOp, MaPLe)CLIP · OSDG averageH-score: 69.40 -> 41.65 (CoOp)Hurt
use SeeCLIP in standard closed-set DG instead of ODG-CLIPSeeCLIP · standard DG averageaccuracy: 97.28 -> 97.78Improved

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