AI Paper Atlas

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

Cross-Domain Human Parsing via Adversarial Feature and Label Adaptation

Si Liu, Yao Sun, Defa Zhu, Guanghui Ren, Yu Chen, Jiashi Feng, Jizhong Han

AAAI 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 35 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 structured label adversarial adaptation to feature adaptation (ablation)Cross-domain human parsing · IndoorAvg. F1: 51.59 -> 51.73Improved
Add feature adversarial adaptation to structured label adaptation (ablation)Cross-domain human parsing · IndoorAvg. F1: 50.95 -> 51.73Improved
Add structured label adversarial adaptation to feature adaptation (ablation)Cross-domain human parsing · Daily VideoAvg. F1: 63.40 -> 64.36Improved
Add feature adversarial adaptation to structured label adaptation (ablation)Cross-domain human parsing · Daily VideoAvg. F1: 63.62 -> 64.36Improved
Add structured label adversarial adaptation to feature adaptation (ablation)Cross-domain human parsing · PridAAvg. F1: 77.39 -> 77.92Improved
Add feature adversarial adaptation to structured label adaptation (ablation)Cross-domain human parsing · PridAAvg. F1: 77.14 -> 77.92Improved
Add structured label adversarial adaptation to feature adaptation (ablation)Cross-domain human parsing · PridBAvg. F1: 77.28 -> 77.89Improved
Add feature adversarial adaptation to structured label adaptation (ablation)Cross-domain human parsing · PridBAvg. F1: 75.89 -> 77.89Improved
Use combined feature and structured label adaptation instead of source-only trainingCross-domain human parsing · IndoorAvg. F1: 49.70 -> 51.73Improved
Use combined feature and structured label adaptation instead of DANNCross-domain human parsing · Daily VideoAvg. F1: 62.84 -> 64.36Improved
Use combined feature and structured label adaptation instead of source-only trainingCross-domain human parsing · PridAAvg. F1: 76.00 -> 77.92Improved
Use combined feature and structured label adaptation instead of DANNCross-domain human parsing · PridBAvg. F1: 75.83 -> 77.89Improved

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