AI Paper Atlas

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

Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation

Yabin Zhang, Bin Deng, Kui Jia, Lei Zhang

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 78 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 augmented anchors (virtual instances) to label propagationLP · Office-31 (average of 6 tasks)accuracy: 84.0 -> 87.4Improved
add augmented anchors (virtual instances) to label propagationLP · ImageCLEF-DA (average of 6 tasks)accuracy: 84.6 -> 88.9Improved
add augmented anchors (virtual instances) to label propagationLP (ResNet-50) · VisDA-2017 (synthetic to real)accuracy: 69.8 -> 78.7Improved
replace pseudo label generator with A2LPMSTN · VisDA-2017 (synthetic to real) (ResNet-50)accuracy: 71.9 -> 81.5Improved
replace pseudo label generator with A2LPMSTN · Office-31 (average of 6 tasks)accuracy: 88.5 -> 89.8Improved
replace pseudo label generator with A2LPCAN · Office-31 (average of 6 tasks)accuracy: 90.3 -> 90.7Improved
replace pseudo label generator with A2LPCAN · VisDA-2017 (synthetic to real) (ResNet-101)accuracy: 87.2 -> 87.6No clear effect
add entropy-based instance weights (ablation)A2LP · Office-31 A to Waccuracy: 87.4 -> 87.7Improved
add entropy-based instance weights (ablation)A2LP · Office-31 W to Aaccuracy: 75.4 -> 75.9Improved
use all source instances instead of K source class centers (ablation)A2LP · VisDA-2017-Smallaccuracy: 77.9 -> 79.3Improved
increase noise level of initial label predictions from 0% to 100% (ablation)A2LP · ImageCLEF-DA P to Caccuracy: 92.8 -> 90.0Hurt
raise alpha from 0.75 to 2.0 (ablation)A2LP · ImageCLEF-DA P to Caccuracy: 95.8 -> 16.8Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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