AI Paper Atlas

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

Discriminative Partial Domain Adversarial Network

Jian Hu, Hongya Tuo, Chao Wang, Lingfeng Qiao, Haowen Zhong, Junchi Yan, Zhongliang Jing, Henry Leung

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 27 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 hard binary weight in place of soft weight (ablation)DPDAN · Office-31 partial DA (31 to 10 classes, average of 6 tasks)accuracy: 92.34 -> 97.51Improved
add hard binary weight in place of soft weight (ablation)DPDAN · VisDA2017 partial DA (S to R, 12 to 6 classes)accuracy: 53.66 -> 65.26Improved
add negative domain discriminator (ablation)DPDAN · Office-31 partial DA (31 to 10 classes, average of 6 tasks)accuracy: 96.14 -> 97.51Improved
add negative domain discriminator (ablation)DPDAN · VisDA2017 partial DA (S to R, 12 to 6 classes)accuracy: 60.12 -> 65.26Improved
use DPDAN instead of PADA for partial adaptationPADA · Office-31 partial DA (31 to 10 classes, average of 6 tasks)accuracy: 92.69 -> 97.51Improved
use DPDAN instead of PADA for partial adaptationPADA · VisDA2017 partial DA (S to R, 12 to 6 classes)accuracy: 53.53 -> 65.26Improved
apply DPDAN in standard domain adaptation instead of RTNRTN · Office-10 to Caltech-10 standard DA (average of 6 tasks)accuracy: 96.31 -> 96.60Improved
apply DPDAN in standard domain adaptation instead of RTNRTN · VisDA2017 standard DA (S to R)accuracy: 63.80 -> 64.51Improved

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