AI Paper Atlas

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

TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation

Mattia Litrico, Mario Valerio Giuffrida, Sebastiano Battiato, Devis Tuia

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 0 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 language-guided soft-contrastive loss to pseudo-label training (ablation)pseudo-labels only · GeoNetavg accuracy: 62.31 -> 65.38Improved
add standard hard contrastive loss to pseudo-label training (ablation)pseudo-labels only · GeoNetavg accuracy: 62.31 -> 62.86No clear effect
add CLIP-based uncertainty estimation to pseudo-label training (ablation)pseudo-labels only · GeoNetavg accuracy: 62.31 -> 63.41Improved
add CLIP uncertainty on top of soft-contrastive loss (ablation)TRUST · GeoNetavg accuracy: 65.38 -> 66.40Improved
generate pseudo-labels with source-finetuned BERT instead of CLIP zero-shot (ablation)TRUST · GeoImnetaccuracy: 61.36 -> 66.40Improved
generate pseudo-labels with BERT instead of source-finetuned CLIP (ablation)TRUST · GeoImnetaccuracy: 63.32 -> 66.40Improved
generate pseudo-labels with BERT instead of CLIP-Text (ablation)TRUST · GeoImnetaccuracy: 64.11 -> 66.40Improved
use TRUST instead of LaGTranLaGTran · DomainNet-345 (average)accuracy: 72.41 -> 74.95Improved
use TRUST instead of LaGTranLaGTran · GeoNet (total average)accuracy: 60.24 -> 63.20Improved
use TRUST instead of PADCLIPPADCLIP · VisDAaccuracy: 88.5 -> 90.6Improved
use TRUST in non-real to real transfers on DomainNet versus CLIPCLIP · DomainNet-345 (non-real to real)accuracyMixed

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