AI Paper Atlas

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

De-Confusing Pseudo-Labels in Source-Free Domain Adaptation

Idit Diamant, Amir Rosenfeld, Idan Achituve, Jacob Goldberger, Arnon Netzer

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 12 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 prior loss on transition matrix (domain adaptation regularization) to DCPL (ablation)SHOT w/ DCPL · VisDAaverage accuracy: 85.9 -> 86.7Improved
add prior loss on transition matrix to DCPL (ablation)SHOT w/ DCPL · DomainNet-126average accuracy: 69.3 -> 69.6Improved
add prior loss on transition matrix to DCPL (ablation)SHOT w/ DCPL · OfficeHomeaverage accuracy: 77.4 -> 77.5Improved
use a stronger pseudo-labeling network (SwinB-22K-1K instead of SwinB-1K) (ablation)SHOT w/ DCPL · OfficeHomeaverage accuracy: 77.5 -> 83.8Improved
use a stronger pseudo-labeling network (SwinB-22K-1K instead of SwinB-1K) (ablation)SHOT w/ DCPL · DomainNet-126average accuracy: 69.6 -> 73.7Improved
use a stronger pseudo-labeling network (SwinB-22K-1K instead of SwinB-1K) (ablation)SHOT++ w/ DCPL · OfficeHomeaverage accuracy: 77.8 -> 83.8Improved
learn the noise transition matrix instead of fixing it to identity (ablation)SHOT w/ DCPL · DomainNet-126 (SwinB-1K)average accuracy: 65.3 -> 69.6Improved
learn the noise transition matrix instead of fixing it to identity (ablation)SHOT w/ DCPL · DomainNet-126 (SwinB-22K-1K)average accuracy: 71.5 -> 73.7Improved
use the true (oracle) transition matrix instead of the learned one (ablation)SHOT w/ DCPL · DomainNet-126 (SwinB-1K)average accuracy: 69.6 -> 72.5Improved
replace Co-learning cross-entropy with DCPL cross-entropySHOT · DomainNet-126average accuracy: 67.6 -> 69.6Improved
replace Co-learning with DCPLSHOT++ · OfficeHomeaverage accuracy: 76.1 -> 77.8Improved
replace Co-learning with DCPLSHOT++ · DomainNet-126average accuracy: 69.3 -> 70.5Improved

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