AI Paper Atlas

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

Forget More to Learn More: Domain-specific Feature Unlearning for Semi-supervised and Unsupervised Domain Adaptation

Hritam Basak, Zhaozheng Yin

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 2 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 Gaussian-guided latent alignment (KL loss) (ablation)SSDA framework · Office-Home and DomainNet SSDAaccuracy (%): 70.4 -> 74.8 (Office-Home 1-shot)Improved
add unlearning loss that maximizes uncertainty on reconstructed images (ablation)SSDA framework · Office-Home and DomainNet SSDAaccuracy (%): 68.5 -> 74.8 (Office-Home 1-shot)Improved
add reconstruction loss to keep structural similarity (ablation)SSDA framework · Office-Home and DomainNet SSDAaccuracy (%): 71.1 -> 74.8 (Office-Home 1-shot)Improved
add Gaussian-guided latent alignment for UDA (ablation)UDA framework (ViT) · Office-Home and DomainNet UDAaccuracy (%): 82.2 -> 88.8 (Office-Home)Improved
add unlearning loss for UDA (ablation)UDA framework (ViT) · Office-Home and DomainNet UDAaccuracy (%): 80.8 -> 88.8 (Office-Home)Improved
add reconstruction loss for UDA (ablation)UDA framework (ViT) · Office-Home and DomainNet UDAaccuracy (%): 84.1 -> 88.8 (Office-Home)Improved
use transformer backbone instead of ResNetUDA framework · Office-Home and DomainNet UDAaccuracy (%): 74.1 -> 88.8 (ResNet vs ViT, Office-Home)Improved
increase unlearning weight gamma relative to reconstruction weight beta (ablation)reconstruction network · visual reconstruction gridretained structure vs domain-specific featuresMixed
apply method with ViT on Office-Home UDA compared to PMTrans-ViTUDA framework · Office-Home UDA (ViT)avg accuracy (%): 88.8 -> 88.8No clear effect

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