AI Paper Atlas

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

Homeomorphism Alignment for Unsupervised Domain Adaptation

Lihua Zhou, Mao Ye, Xiatian Zhu, Siying Xiao, Xu-Qian Fan, Ferrante Neri

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 19 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
use INN homeomorphism instead of ordinary bijection with two networks (ablation)HMA(CAN) · Office-31 A->Daccuracy (%): 90.3 -> 95.8Improved
use INN instead of two networks reduces parameters (ablation)HMA(CAN) · Office-31parameters: 33603584 -> 20992000Improved
add INN mapping alone with source retraining (ablation)CAN · Office-31accuracy (%): A->W 94.5 -> 94.1No clear effect
train in target space with transformed source features (S2T) (ablation)INN(DAN) · Office-31 D->Aaccuracy (%): 62.9 -> 66.5Improved
add target prediction consistency (T2S) (ablation)INN(DAN)+S2T · Office-31 D->Aaccuracy (%): 66.5 -> 67.9Improved
use class-conditional sewing (CAN) instead of marginal (DAN) matching (ablation)HMA · Office-31avg accuracy (%): 83.9 -> 91.2Improved
apply HMA on top of CANCAN · Office-Homeavg accuracy (%): 71.8 -> 73.2Improved
apply HMA on top of DANNDANN · Office-Homeavg accuracy (%): 57.6 -> 62.7Improved
apply HMA on top of DANDAN · Office-31avg accuracy (%): 80.4 -> 83.9Improved
HMA(CAN) vs ATDOC on Office-HomeHMA(CDAN) · Office-Homeavg accuracy (%): HMA(CDAN) 71.7 vs ATDOC 72.2Mixed

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