AI Paper Atlas

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

Unsupervised Domain Adaptation via Discriminative Manifold Propagation

You-Wei Luo, Chuan-Xian Ren, Dao‐Qing Dai, Hong Yan

TPAMI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 98 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 manifold metric alignment loss (ablation)DMP · VisDA-2017 (vanilla)accuracy (%): 69.7 -> 79.3Improved
add discriminative structure loss (ablation)DMP · VisDA-2017 (vanilla)accuracy (%): 71.1 -> 79.3Improved
add manifold metric alignment loss (ablation)DMP · Office-31 (vanilla)accuracy (%): 84.1 -> 87.4Improved
add discriminative structure loss (ablation)DMP · Office-31 (vanilla)accuracy (%): 82.3 -> 87.4Improved
add manifold metric alignment loss (ablation)DMP · Office-Home (vanilla)accuracy (%): 67.1 -> 68.1Improved
add discriminative structure loss (ablation)DMP · Office-Home (vanilla)accuracy (%): 66.3 -> 68.1Improved
add manifold metric alignment loss (ablation)DMP · ImageCLEF (vanilla)accuracy (%): 87.3 -> 89.1Improved
add discriminative structure loss (ablation)DMP · ImageCLEF (vanilla)accuracy (%): 86.8 -> 89.1Improved
use affine Grassmann instead of Grassmann manifold (partial setting) (ablation)DMP · ImageCLEF (partial)accuracy (%): 90.5 -> 87.9Hurt
use Log-Euclidean instead of Grassmann manifold (partial setting) (ablation)DMP · ImageCLEF (partial)accuracy (%): 90.5 -> 88.9Hurt
vary manifold type among Grassmann, affine Grassmann, Log-Euclidean (vanilla) (ablation)DMP · ImageCLEF (vanilla)accuracy (%): 89.1, 88.9, 89.1No clear effect
add entropy term to DMP for partial UDADMP+ent · Office-Home (partial)accuracy (%): 66.5 -> 73.5Improved

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