AI Paper Atlas

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

Gradient Distribution Alignment Certificates Better Adversarial Domain Adaptation

Zhiqiang Gao, Shufei Zhang, Kaizhu Huang, Qiufeng Wang, Chaoliang Zhong

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 63 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 feature gradient alignment on top of DANN (ablation)DANN · Office-31 (average)accuracy: 82.2 -> 88.9Improved
add feature gradient alignment on top of CDAN-E (ablation)CDAN-E · Office-31 (average)accuracy: 87.7 -> 89.2Improved
add feature gradient alignment on top of MDD (ablation)MDD · Office-31 (average)accuracy: 88.9 -> 90.6Improved
add feature gradient alignment on top of MDD (ablation)MDD · Office-Home (average)accuracy: 68.1 -> 71.5Improved
add self-supervised pseudo-labeling (ablation)FGDA · Office-31 (average)accuracy: 86.0 -> 88.6Improved
add Jacobian regularization (ablation)FGDA · Office-31 (average)accuracy: 88.3 -> 88.6Improved
add both Jacobian regularization and pseudo-labeling (ablation)FGDA · Office-31 (average)accuracy: 85.0 -> 88.6Improved
gradient alignment alone replaces DANN feature alignment (ablation)FGDA w/o FJR, SPL · Office-31 (average)accuracy: 82.2 -> 85.0Improved
use cross-entropy instead of conditional entropy for target gradients (ablation)FGDA+DANN · Office-31 (average)accuracy: 87.6 -> 88.9Improved
use FGDA alone instead of MDDFGDA · Office-31 (average)accuracy: 88.9 -> 88.6No clear effect
use FGDA alone instead of MDDFGDA · Office-Home (average)accuracy: 68.1 -> 68.3No clear effect
vary Jacobian regularization weight lambda2 from 0.005 to 0.010 (ablation)FGDA w/o SPL · Office-31 A->Waccuracy: 85.0 -> 91.3Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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