Research map / Label-efficient and robust learning / Domain adaptation and generalization
Source-Free Progressive Graph Learning for Open-Set Domain Adaptation
Yadan Luo, Zijian Wang, Zhuoxiao Chen, Zi Helen Huang, Mahsa Baktashmotlagh
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 progressive pseudo-labeling (ablation) | PGL · Syn2Real-O | OS*: 55.3 -> 66.8 | Improved |
| use edge loss in addition to node classification loss (ablation) | PGL · Syn2Real-O | OS*: 57.6 -> 66.8 | Improved |
| add graph neural networks (ablation) | PGL · Syn2Real-O | OS*: 58.5 -> 66.8 | Improved |
| add mix-up strategy (ablation) | PGL · Syn2Real-O | OS*: 63.6 -> 66.8 | Improved |
| add mix-up strategy (ablation) | PGL · Syn2Real-O | UNK: 49.8 -> 49.6 | No clear effect |
| reduce enlarging factor alpha from 0.20 to 0.05 (ablation) | PGL · Syn2Real-O | OS*: 63.3 -> 66.5 | Improved |
| reduce enlarging factor alpha from 0.20 to 0.05 (ablation) | PGL · Office-Home Ar->Cl | OS*: 61.1 -> 63.1 | Improved |
| add balanced pseudo-labeling (BP-L) (ablation) | SF-PGL · VisDA-17 (ResNet-50) | OS*: 83.8 -> 94.7 | Improved |
| add balanced pseudo-labeling (BP-L) (ablation) | SF-PGL · VisDA-17 (ResNet-50) | UNK: 72.0 -> 68.6 | Hurt |
| reduce enlarging factor alpha from 0.2 to 0.05 (ablation) | SF-PGL · Syn2Real-O (ResNet-50) | OS*: 73.0 -> 83.6 | Improved |
| add adversarial learning (ablation) | PGL · HMDB->UCF full | OS: 70.0 -> 81.3 | Improved |
| add adversarial learning (ablation) | PGL · UCF->HMDB full | OS: 62.8 -> 69.8 | Improved |
Closest papers by meaning
- Progressive Graph Learning for Open-Set Domain Adaptation (ICML 2020 · similarity 0.93)
- Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-training (IJCV 2024 · similarity 0.91)
- Domain Adaptation under Open Set Label Shift (NeurIPS 2022 · similarity 0.90)
- LEARNING FACTORIZED REPRESENTATIONS FOR OPEN-SET DOMAIN ADAPTATION (ICLR 2019 · similarity 0.89)
- Unraveling the Mysteries of Label Noise in Source-Free Domain Adaptation: Theory and Practice (TPAMI 2025 · similarity 0.89)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.88)
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.
