AI Paper Atlas

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

On the Transferability and Discriminability of Representation Learning in Unsupervised Domain Adaptation

Wenwen Qiang, Ziyin Gu, Lingyu Si, Jiangmeng Li, Changwen Zheng, Fuchun Sun, Hui Xiong

TPAMI 2025 · 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 local consistency module (RLGC to RLGLC) (ablation)RLGC · Office-31accuracy (%): 90.3 -> 92.5Improved
add local consistency module (RLGC to RLGLC) (ablation)RLGC · Office-Homeaccuracy (%): 71.2 -> 74.3Improved
add local consistency module (RLGC to RLGLC) (ablation)RLGC · VisDA-2017accuracy (%): 84.9 -> 89.4Improved
plug local consistency module (LM) into DANN (ablation)DANN · VisDA-2017accuracy (%): 57.4 -> 58.4Improved
plug local consistency module (LM) into SWD (ablation)SWD · VisDA-2017accuracy (%): 76.4 -> 77.6Improved
plug local consistency module (LM) into CAN (ablation)CAN · VisDA-2017accuracy (%): 87.2 -> 88.3Improved
plug local consistency module (LM) into CAN, truck class (ablation)CAN · VisDA-2017 (truck class)accuracy (%): 59.9 -> 60.5Improved
RLGC* variant over RLGCRLGC · Office-31accuracy (%): 90.3 -> 91.2Improved
RLGC* variant over RLGCRLGC · Office-Homeaccuracy (%): 71.2 -> 72.7Improved
RLGC* variant over RLGCRLGC · VisDA-2017accuracy (%): 84.9 -> 87.3Improved
RLGLC vs best baseline TransVQA (ViT-B backbone)TransVQA · Office-31accuracy (%): 92.2 -> 92.5Improved
RLGLC vs best baseline SAMB-DSAMB-D · Office-Homeaccuracy (%): 72.6 -> 74.3Improved

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