AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Dual Adaptive Representation Alignment for Cross-Domain Few-Shot Learning

Yifan Zhao, Tong Zhang, Jia Li, Yonghong Tian

TPAMI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot · 63 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 prototypical feature alignment (PFA) to Ridge baseline (ablation)Dara · CropDiseases 5-way 5-shotaccuracy: 73.83 -> 93.55Improved
add normalized distribution alignment (mean statistics) to Ridge baseline (ablation)Dara · EuroSAT 5-way 5-shotaccuracy: 63.18 -> 81.25Improved
add NDA on top of Ridge+PFA (ablation)Dara · ISIC 5-way 5-shotaccuracy: 51.70 -> 56.28Improved
use query statistics instead of support statistics for normalization (BN) (ablation)Dara NDA · CropDiseases 5-way 5-shotaccuracy: 93.55 -> 94.49Improved
use query statistics instead of support statistics for normalization (BN) (ablation)Dara NDA · ISIC 5-way 5-shotaccuracy: 51.69 -> 51.29Hurt
replace mean fusion (0.5,0.5) with learnable gating (ablation)Dara NDA · ISIC 5-way 5-shotaccuracy: 53.84 -> 56.28Improved
add instance recalibration to prototypical reprojection (ablation)Dara PFA · ISIC 5-way 5-shotaccuracy: 55.40 -> 56.28Improved
use only one query sample for statistics (S+Q-1) instead of all queries (ablation)Dara NDA · ISIC 5-way 5-shotaccuracy: 55.12 vs 56.28No clear effect
optimize only reprojection weights Z from pretrained init (ablation)Dara meta-finetuning · CropDiseases 5-way 5-shotaccuracy: 73.83 -> 94.42Improved
add backbone optimization to Z optimization (two-stage) (ablation)Dara meta-finetuning · EuroSAT 5-way 5-shotaccuracy: 83.94 -> 85.84Improved
use smaller pseudo support (5% support / 95% query) split instead of 20/80 (query/support) (ablation)Dara meta-finetuning · ISIC 5-way 20-shotaccuracy: 69.12 -> 67.36Hurt
increase feature resolution from 3x3 to 7x7 (ablation)Dara PFA · ChestX 5-way 5-shotaccuracy: 27.57 -> 26.00Hurt

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