Research map / Label-efficient and robust learning / Noisy labels
When Source-Free Domain Adaptation Meets Learning with Noisy Labels
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ELR to Source Only self-training | Source Only · Office-Home (12 transfer tasks, Avg) | accuracy (%): 60.2 -> 67.3 | Helped |
| Add ELR to SHOT | SHOT · Office-Home (12 transfer tasks, Avg) | accuracy (%): 71.8 -> 72.6 | Helped |
| Add ELR to G-SFDA | G-SFDA · Office-Home (12 transfer tasks, Avg) | accuracy (%): 70.7 -> 71.1 | Helped |
| Add ELR to NRC | NRC · Office-Home (12 transfer tasks, Avg) | accuracy (%): 70.8 -> 72.6 | Helped |
| Add ELR to Source Only self-training | Source Only · DomainNet (12 transfer tasks, Avg) | accuracy (%): 61.0 -> 73.8 | Helped |
| Add ELR to SHOT | SHOT · DomainNet (12 transfer tasks, Avg) | accuracy (%): 77.7 -> 79.7 | Helped |
| Add ELR to G-SFDA | G-SFDA · DomainNet (12 transfer tasks, Avg) | accuracy (%): 72.8 -> 74.6 | Helped |
| Add ELR to NRC | NRC · DomainNet (12 transfer tasks, Avg) | accuracy (%): 76.4 -> 79.4 | Helped |
| Add ELR to Source Only self-training | Source Only · VisDA-C (Synthesis → Real) | Per-class accuracy (%): 46.6 -> 74.6 | Helped |
| Add ELR to SHOT | SHOT · VisDA-C (Synthesis → Real) | Per-class accuracy (%): 82.9 -> 84.1 | Mixed |
| Add ELR to G-SFDA | G-SFDA · VisDA-C (Synthesis → Real) | Per-class accuracy (%): 84.8 -> 86.4 | Mixed |
| Add ELR to NRC | NRC · VisDA-C (Synthesis → Real) | Per-class accuracy (%): 85.4 -> 85.8 | Mixed |
Closest papers by meaning
- Discretized Density-Guided Source-Free Domain Adaptation for Regression (ICML 2026 · similarity 0.92)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.91)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.91)
- Proxy Denoising for Source-Free Domain Adaptation (ICLR 2025 · similarity 0.90)
- SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation (ICLR 2024 · similarity 0.89)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 2025 · similarity 0.89)
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.