AI Paper Atlas

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

Adversarial Feature Augmentation for Cross-Domain Few-Shot Classification

Yanxu Hu, Andy J. Ma

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification

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 AFA module to GNNGNN · CUB 5-shotaccuracy (%): 62.87 -> 68.25Improved
add AFA module to meta-learning baselinesMN, GNN, TPN · eight target datasets, 1-shotaccuracy (%): 3.45%Improved
add AFA module to meta-learning baselinesMN, GNN, TPN · eight target datasets, 5-shotaccuracy (%): 4.25%Improved
use AFA instead of ATAmeta-learning baselines · eight target datasetsaccuracy (%): about 1%Improved
add domain discriminator to AFA (ablation)MN+AFA · eight target datasets, 1-shotaccuracy (%): 2.48%Improved
add domain discriminator to AFA (ablation)MN+AFA · CUB 5-shotaccuracy (%): 58.06 -> 59.46Improved
add gram-matrix loss to AFA (ablation)MN+AFA · eight target datasetsaccuracy (%): 2.57%Improved
add gram-matrix loss to AFA (ablation)MN+AFA · CUB 5-shotaccuracy (%): 56.44 -> 59.46Improved
replace linear mean/variance perturbation with non-linear convolution (ablation)MN+AFA · CUB 5-shotaccuracy (%): 59.46 -> 50.17Hurt
replace linear perturbation with non-linear convolution (ablation)MN+AFA · CUB 1-shotaccuracy (%): 41.02 -> 34.42Hurt
AFA trained without domain discriminator (classification loss only) (ablation)MN · CropDiseasesaccuracy (%): declines vs baseline MNHurt
use meta-learning with AFA instead of pre-train and fine-tuningGNN · CUB 5-shotaccuracy (%): 63.76 -> 70.33Improved

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