AI Paper Atlas

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

Towards Effective Foundation Model Adaptation for Extreme Cross-Domain Few-Shot Learning

Fei Zhou, Peng Wang, Lei Zhang, Wei Wei, Chen Ding, Guosheng Lin, Yanning Zhang

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 2 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 masked cross-model unidirectional reconstruction (MCR) (ablation)F-ViT fine-tuning · Extreme CD-FSL average 1-shotaccuracy (%): 39.70 -> 41.96Improved
add masked cross-model unidirectional reconstruction (MCR) (ablation)F-ViT fine-tuning · Extreme CD-FSL average 5-shotaccuracy (%): 64.20 -> 65.06Improved
add decision graph association (DGA) (ablation)F-ViT fine-tuning · Extreme CD-FSL average 1-shotaccuracy (%): 39.70 -> 42.03Improved
add decision graph association (DGA) (ablation)F-ViT fine-tuning · Extreme CD-FSL average 5-shotaccuracy (%): 64.20 -> 64.99Improved
combine MCR and DGA rather than either alone (ablation)F-ViT fine-tuning · Extreme CD-FSL average 1-shotaccuracy (%): 39.70 -> 43.35Improved
add MCR on ISIC (ablation)F-ViT fine-tuning · ISIC 1-shotaccuracy (%): 26.35 -> 32.27Improved
add DGA on ISIC (ablation)F-ViT fine-tuning · ISIC 1-shotaccuracy (%): 26.35 -> 33.11Improved
replace plain MAE reconstruction with cross-model unidirectional reconstruction plus DGA (ablation)F-ViT fine-tuning · Extreme CD-FSL average 1-shotaccuracy (%): 41.49 -> 43.35Improved
replace bidirectional MAE with unidirectional reconstruction (ablation)F-ViT fine-tuning · Extreme CD-FSL average 1-shotaccuracy (%): 40.56 -> 43.35Improved
replace feature or logits distillation with MCR plus DGA (ablation)F-ViT fine-tuning · Extreme CD-FSL average 1-shotaccuracy (%): 39.90 -> 43.35Improved
replace decision fusion with MCR plus DGA (ablation)F-ViT fine-tuning · Extreme CD-FSL average 1-shotaccuracy (%): 35.13 -> 43.35Improved
jointly train expert T-ViT to guide F-ViT instead of T-ViT alone (ablation)T-ViT · Extreme CD-FSL average 1-shotaccuracy (%): 27.71 -> 43.35Improved

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