AI Paper Atlas

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

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

Wentao Chen, Zhang Zhang, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain text and graph transfer

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 strong augmentation to source-only training (ablation)stabPA · DomainNet real-sketch 1-shotaccuracy: 40.23 -> 41.74Improved
add source-to-target alignment (ablation)stabPA · DomainNet real-sketch 1-shotaccuracy: 40.23 -> 42.86Improved
add target-to-source alignment (ablation)stabPA · DomainNet real-sketch 1-shotaccuracy: 40.23 -> 44.20Improved
combine both alignments (ablation)stabPA · DomainNet real-sketch 1-shotaccuracy: 44.20 -> 47.01Improved
add strong augmentation to bi-directional alignment (ablation)stabPA · DomainNet real-sketch 1-shotaccuracy: 47.01 -> 50.85Improved
add strong augmentation to bi-directional alignment (ablation)stabPA · DomainNet real-sketch 5-shotaccuracy: 56.68 -> 61.37Improved
add strong augmentation to bi-directional alignment (ablation)stabPA · DomainNet sketch-real 5-shotaccuracy: 64.32 -> 68.93Improved
use 100% instead of 10% of unlabeled samples (ablation)stabPA · DomainNet avg 1-shotaccuracy: 51.76 -> 53.92Improved
use 10% unlabeled samples vs FixMatch with 100%stabPA · DomainNet avg 5-shotaccuracy: 62.58 -> 65.96Improved
include unlabeled data from base classes (0% to 100% of classes) (ablation)stabPA · DomainNet avg 1-shotaccuracy: 50.74 -> 53.92Improved
set interpolation coefficient lambda 0.2 instead of 0.0 (ablation)stabPA · DomainNet real-painting 5-shotaccuracy: 64.95 -> 65.65Improved
raise interpolation coefficient lambda from 0.2 to 1.0 (ablation)stabPA · DomainNet real-painting 5-shotaccuracy: 65.65 -> 60.60Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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