AI Paper Atlas

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

How Does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?

Li Zhong, Zhen Fang, Feng Liu, Jie Lu, Bo Yuan, Guangquan Zhang

AAAI 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 46 citations (OpenAlex)

Read the paper

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 the combined-risk proxyDAN · Office-Homeaverage accuracy: 64.7 -> 68.6Improved
Add the combined-risk proxyDANN · Office-Homeaverage accuracy: 61.3 -> 66.8Improved
Add the combined-risk proxyCDAN+E · Office-Homeaverage accuracy: 65.2 -> 67.8Improved
Add the combined-risk proxySymNets · Office-Homeaverage accuracy: 67.2 -> 68.2Improved
Use target augmentation without mixup (ablation)E-MixNet · Image-CLEFaverage accuracy: 89.9 vs 91.0Hurt
Use target augmentation with mixup but no source augmentation (ablation)E-MixNet · Image-CLEFaverage accuracy: 90.2 vs 91.0Hurt
Replace e-mixup with mixup (ablation)E-MixNet · Image-CLEFaverage accuracy: 90.8 vs 91.0Hurt
Add source augmentation to target augmentation with mixup (ablation)E-MixNet · Image-CLEFaverage accuracy: 90.2 -> 90.8Improved

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