Research map / Label-efficient and robust learning / Domain adaptation and generalization
Discriminative Noise Robust Sparse Orthogonal Label Regression-Based Domain Adaptation
Lingkun Luo, Shiqiang Hu, Liming Chen
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 discriminative force terms (CDDA+) to JDA (ablation) | JDA · CMU PIE | accuracy: 60.24 -> 63.22 | Improved |
| add NRS_OLR term to JDA (JOLR-DA) (ablation) | JDA · CMU PIE | accuracy: 60.24 -> 69.96 | Improved |
| jointly add discriminative force and NRS_OLR (DOLL-DA) (ablation) | JDA · CMU PIE | accuracy: 60.24 -> 82.50 | Improved |
| add data distribution alignment to OLR classifier (ablation) | OLR · CMU PIE | accuracy: 55.88 -> 60.24 | Improved |
| add discriminative force terms only (ablation) | JDA · Office-Home | accuracy: +0.19 point | No clear effect |
| add NRS_OLR term to JDA (ablation) | JDA · Office-Home | accuracy: 44.48 | Improved |
| add NRS_OLR to CDDA+ (full DOLL-DA) (ablation) | CDDA+ · Office-Home | accuracy: +11.07 points | Improved |
| add discriminative force terms (ablation) | JDA · USPS+MNIST (shallow) | accuracy: 69.14 | Improved |
| jointly add both terms (DOLL-DA) (ablation) | JDA · USPS+MNIST (shallow) | accuracy: 77.82 | Improved |
| use shallow-feature DOLL-DA versus deep DANN | DANN · USPS+MNIST | accuracy: +2 points | Improved |
| jointly add both terms (DOLL-DA) (ablation) | JDA · SVHN-MNIST | accuracy: +22 points | Improved |
| jointly add both terms (DOLL-DA) (ablation) | JDA · Office+Caltech (SURF) | accuracy: 51.18 | Improved |
Closest papers by meaning
- Label-Noise Robust Domain Adaptation (ICML 2020 · similarity 0.90)
- Unraveling the Mysteries of Label Noise in Source-Free Domain Adaptation: Theory and Practice (TPAMI 2025 · similarity 0.89)
- De-Confusing Pseudo-Labels in Source-Free Domain Adaptation (ECCV 2024 · similarity 0.89)
- Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization (AAAI 2024 · similarity 0.87)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.87)
- Invertible Projection and Conditional Alignment for Multi-Source Blended-Target Domain Adaptation (AAAI 2025 · 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.
