AI Paper Atlas

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

Progressive Distribution Bridging: Unsupervised Adaptation for Large-scale Pre-trained Models via Adaptive Auxiliary Data

Weinan He, Yixin Zhang, Zilei Wang

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real 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 progressive auxiliary data (alpha 0.1, 0.4, 0.7) in order vs reversed order (ablation)PDB · DomainNetavg accuracy (%): 62.82 -> 63.10Improved
use progressive styles instead of target-style data only (ablation)PDB · DomainNetavg accuracy (%): 62.80 -> 63.10Improved
add retrieved auxiliary data to target-only training (ablation)PDB · DomainNetavg accuracy (%): 62.21 -> 63.10Improved
replace labeled UDA source domain with retrieved adaptive auxiliary data (ablation)PDB · DomainNetavg accuracy (%): 62.80 -> 63.10Improved
add Style filter to T2T retrieval (ablation)cascaded semantic filters · DomainNet (alpha=0.1)avg accuracy (%): 60.80 -> 61.09Improved
combine Style, CM and GMM filters (ablation)cascaded semantic filters · DomainNet (alpha=0.1)avg accuracy (%): 60.80 -> 61.53Improved
add a fourth alpha step (1.0) (ablation)PDB · DomainNet (->Q)accuracy (%): 22.82 -> 22.89No clear effect
increase auxiliary samples per category beyond Nmax = 100 (ablation)PDB · DomainNetaccuracyNo clear effect
use multi-step progressive alpha vs single alpha 0.1 (ablation)PDB · DomainNet (->Q)accuracy (%): 21.10 -> 22.82Improved
use PDB instead of UFT POUF-FTCLIP · Office-Homeavg accuracy (%): 86.1 -> 87.8Improved
use PDB instead of labeled-source UDA methodsCLIP · DomainNetavg accuracy (%): 63.7 -> 63.1No clear effect
use PDB instead of UFT POUF-FT on poor-initial-performance domainCLIP · DomainNet (->Q)accuracy (%): 18.8 -> 22.8Improved

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