AI Paper Atlas

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

Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization

Guoliang Kang, Liang Zheng, Yan Yan, Yi Yang

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 127 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 attention alignment loss L_AT (ablation)EM target training · MNIST->MNIST-Maccuracy (%): 93.5 -> 95.6Improved
add attention alignment loss L_AT to a CNN trained on S+Tf (ablation)CNN · MNIST->MNIST-Maccuracy (%): 78.5 -> 85.7Improved
add synthetic target data to source network training (ablation)CNN · MNIST->MNIST-Maccuracy (%): 45.6 -> 75.0Improved
mix source and synthetic target data (ablation)CNN · MNIST->MNIST-Maccuracy (%): 75.0 -> 78.5Improved
add attention alignment loss L_AT (ablation)EM, Office-31 4 tasks · D->Aaccuracy (%): 72.3 -> 74.3Improved
add attention alignment loss L_AT (ablation)EM, Office-31 4 tasks · W->Aaccuracy (%): 72.2 -> 73.9Improved
add attention alignment loss L_AT (ablation)EM, Office-31 average of 6 tasks · Office-31accuracy (%): 86.3 -> 87.2Improved
add asynchronous update of M_post (full vs EM-A) (ablation)EM · Office-31 4 tasks avgaccuracy (%): 64.4 -> 79.7Improved
add learning-rate schedule re-initialization (full vs EM-C) (ablation)EM · Office-31 4 tasks avgaccuracy (%): 78.6 -> 79.7Improved
add filtering of noisy data (full vs EM-B) (ablation)EM · Office-31 4 tasks avgaccuracy (%)Improved
use L2 attention discrepancy instead of L1 (ablation)L_AT · Office-31 4 tasks avgaccuracy (%)Improved
use L2 attention discrepancy instead of JMMD (ablation)L_AT · Office-31 4 tasks avgaccuracy (%): 78.1 -> 80.9Improved

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