AI Paper Atlas

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

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment

Yaze Zhao, Yixiong Zou, Yuhua Li, Ruixuan Li

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 3 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 CC-CDFSL cycle-consistency regularizer to CLIP-LoRACLIP-LoRA ViT · CDFSL 5-way 1-shot avgaccuracy (%): 55.89 -> 58.83Improved
add CC-CDFSL to CLIP-LoRACLIP-LoRA ViT · CDFSL 5-way 5-shot avgaccuracy (%): 65.99 -> 67.90Improved
add CC-CDFSL to CoOpCoOp · CDFSL 5-way 5-shot avgaccuracy (%): 60.95 -> 61.44Improved
add CC-CDFSL to MapleMaple · CDFSL 5-way 1-shot avgaccuracy (%): 53.04 -> 54.89Improved
add CC-CDFSL to CLIP-LoRA on ChestXCLIP-LoRA ViT · ChestX 5-way 1-shotaccuracy (%): 21.73 -> 22.21Improved
add all components (T-I-T, I-T-I, SA) (ablation)CLIP-LoRA · CDFSL 5-way 5-shot avgaccuracy (%): 65.98 -> 67.90Improved
use cross-view instead of intra-image retrieval in I-T-I (ablation)CC-CDFSL · CDFSL 5-way 5-shot avgaccuracy (%): 67.25 -> 67.37Improved
use cross-view instead of all-images retrieval in I-T-I (ablation)CC-CDFSL · CDFSL 5-way 5-shot avgaccuracy (%): 67.19 -> 67.37Improved
increase anchor patch number k beyond 13 (ablation)CC-CDFSL · ISIC2018 5-way 5-shotaccuracy (%): 54.72 -> 54.21Hurt
use very small anchor patch number k<=3 (ablation)CC-CDFSL · ISIC2018 5-way 5-shotaccuracy (%): 54.67 -> 54.28Hurt
add cycle consistency to CLIP-LoRA for prototype classificationCLIP-LoRA · CropDiseasesaccuracy (%): 95.85 -> 96.24Improved
add cycle consistency to Maple for base-to-new generalizationMaple · EuroSAT new classesaccuracy (%): +3.6%Improved

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