AI Paper Atlas

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

Mind the Discriminability: Asymmetric Adversarial Domain Adaptation

Jianfei Yang, Han Zou, Yuxun Zhou, Zhaoyang Zeng, Lihua Xie ()

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 50 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
replace symmetric domain classifier with asymmetric autoencoder discriminator (AADA vs DANN)DANN · SVHN->MNISTaccuracy (%): 74.7 -> 98.1Improved
replace symmetric domain classifier with asymmetric autoencoder discriminator (AADA vs DANN)DANN · Office-Homeaccuracy (%): 57.6 -> 65.3Improved
replace symmetric domain classifier with asymmetric autoencoder discriminator (AADA vs DANN)DANN · Image-CLEFaccuracy (%): 85.0 -> 86.5Improved
integrate AADA with CCNCCN · Image-CLEFaccuracy (%): 85.1 -> 88.4Improved
integrate AADA with CCNCCN · Office-Homeaccuracy (%): 59.7 -> 67.0Improved
fix source and push target (AADA) rather than fix target and push source (AADAopt) (ablation)AADA · SVHN->MNISTaccuracy (%): 74.8 -> 98.1Improved
fix source and push target (AADA) rather than fix target and push source (AADAopt) (ablation)AADA · MNIST->MNIST-Maccuracy (%): 47.1 -> 95.5Improved
fix source and push target (AADA) rather than fix target and push source (AADAopt) (ablation)AADA · MNIST->USPSaccuracy (%): 95.6 -> 98.4Improved
increase margin m (ablation)AADA · SVHN->MNISTaccuracy (%)Improved
use large adversarial weight gamma (ablation)AADA vs DANN · SVHN->MNISTaccuracy (%)Mixed
use AADA instead of DANN for spectral discriminabilityAADA · SVHN->MNISTideal joint hypothesis lambdaImproved

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