AI Paper Atlas

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

Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice

Yabin Zhang, Bin Deng, Hui Tang, Lei Zhang, Kui Jia

TPAMI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 102 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 CE surrogate instead of DANN-style binary domain discriminator (ablation)McDalNets · Office-31accuracy (%): 82.8 -> 85.3Improved
use CE surrogate instead of DANN-style binary domain discriminator (ablation)McDalNets · VisDA-2017accuracy (%): 58.4 -> 70.5Improved
use CE surrogate instead of MDD variant (ablation)McDalNets · Office-Homeaccuracy (%): 61.1 -> 64.0Improved
MDD variant (relative margin) on Digits and VisDA-2017 (ablation)McDalNets · Digitsaccuracy (%): not convergeHurt
use CE surrogate instead of KL surrogate (ablation)McDalNets · Digitsaccuracy (%): 82.9 -> 94.9Improved
use CE surrogate instead of L1/MCD surrogate (ablation)McDalNets · Office-Homeaccuracy (%): 62.0 -> 64.0Improved
use CE surrogate instead of L1/MCD surrogate (ablation)McDalNets · VisDA-2017accuracy (%): 70.4 -> 70.5No clear effect
use CE surrogate instead of L1/MCD surrogate (ablation)McDalNets · DomainNetaccuracy (%): 27.7 -> 27.9No clear effect
replace best McDalNets surrogate (CE) with SymmNets-V2 domain confusion and discrimination (ablation)SymmNets-V2 · Office-31accuracy (%): 85.3 -> 89.1Improved
replace best McDalNets surrogate (CE) with SymmNets-V2 (ablation)SymmNets-V2 · Office-Homeaccuracy (%): 64.0 -> 68.1Improved
replace best McDalNets surrogate (CE) with SymmNets-V2 (ablation)SymmNets-V2 · DomainNetaccuracy (%): 27.9 -> 27.9No clear effect
replace best McDalNets surrogate (CE) with SymmNets-V2 (ablation)SymmNets-V2 · VisDA-2017accuracy (%): 70.5 -> 71.3Improved

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