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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add structured label adversarial adaptation to feature adaptation (ablation) | Cross-domain human parsing · Indoor | Avg. F1: 51.59 -> 51.73 | Improved |
| Add feature adversarial adaptation to structured label adaptation (ablation) | Cross-domain human parsing · Indoor | Avg. F1: 50.95 -> 51.73 | Improved |
| Add structured label adversarial adaptation to feature adaptation (ablation) | Cross-domain human parsing · Daily Video | Avg. F1: 63.40 -> 64.36 | Improved |
| Add feature adversarial adaptation to structured label adaptation (ablation) | Cross-domain human parsing · Daily Video | Avg. F1: 63.62 -> 64.36 | Improved |
| Add structured label adversarial adaptation to feature adaptation (ablation) | Cross-domain human parsing · PridA | Avg. F1: 77.39 -> 77.92 | Improved |
| Add feature adversarial adaptation to structured label adaptation (ablation) | Cross-domain human parsing · PridA | Avg. F1: 77.14 -> 77.92 | Improved |
| Add structured label adversarial adaptation to feature adaptation (ablation) | Cross-domain human parsing · PridB | Avg. F1: 77.28 -> 77.89 | Improved |
| Add feature adversarial adaptation to structured label adaptation (ablation) | Cross-domain human parsing · PridB | Avg. F1: 75.89 -> 77.89 | Improved |
| Use combined feature and structured label adaptation instead of source-only training | Cross-domain human parsing · Indoor | Avg. F1: 49.70 -> 51.73 | Improved |
| Use combined feature and structured label adaptation instead of DANN | Cross-domain human parsing · Daily Video | Avg. F1: 62.84 -> 64.36 | Improved |
| Use combined feature and structured label adaptation instead of source-only training | Cross-domain human parsing · PridA | Avg. F1: 76.00 -> 77.92 | Improved |
| Use combined feature and structured label adaptation instead of DANN | Cross-domain human parsing · PridB | Avg. F1: 75.83 -> 77.89 | Improved |
Closest papers by meaning
- Macro-Micro Adversarial Network for Human Parsing (ECCV 2018 · similarity 0.89)
- From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing (TPAMI 2024 · similarity 0.88)
- Deep Learning Technique for Human Parsing: A Survey and Outlook (IJCV 2024 · similarity 0.88)
- End-to-End One-Shot Human Parsing (TPAMI 2023 · similarity 0.88)
- Human Parsing with Contextualized Convolutional Neural Network (TPAMI 2016 · similarity 0.87)
- Look Into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing (CVPR 2017 · similarity 0.87)
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.
