Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation
Check 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 |
|---|---|---|---|
| learn representative cross-domain landmarks using unlabeled target data rather than use the supervised CDLS sup objective (ablation) | CDLS · Office + Caltech-256, SURF ↔ DeCAF6 | accuracy: 86.7±0.6 -> 91.7±0.2; 88.5±1.4 -> 95.2±0.9; 74.8±1.1 -> 81.8±1.1; 45.6±0.7 -> 46.4±1.0; 60.9±1.1 -> 63.1±1.1; 31.6±1.5 - | Helped |
| learn representative cross-domain landmarks using unlabeled target data rather than use the supervised CDLS sup objective (ablation) | CDLS · Office + Caltech-256, SURF → DeCAF6, A→D | accuracy: 92.0±1.2 -> 96.1±0.7 | Helped |
| learn representative cross-domain landmarks using unlabeled target data rather than use the supervised CDLS sup objective (ablation) | CDLS · Office + Caltech-256, DeCAF6 → SURF, A→D | accuracy: 54.3±1.3 -> 58.4±0.8 | Helped |
| vary the number of labeled target examples per class | HDA methods on Multilingual Reuters Collection, Spanish target · Cross-lingual text categorization | accuracy | Helped |
| set the landmark ratio to δ=0 or δ=1 rather than an intermediate value (ablation) | CDLS · Caltech-256 → DSLR, SURF → DeCAF6 | accuracy | Hurt |
| increase reduced subspace dimension m beyond 100 (ablation) | CDLS · Caltech-256 → DSLR, SURF → DeCAF6 | accuracy | No clear effect |
| use the supervised CDLS objective without landmark learning (ablation) | CDLS · Office + Caltech-256 cross-feature object recognition | accuracy | Mixed |
Closest papers by meaning
- Aligning Domain-Specific Distribution and Classifier for Cross-Domain Classification from Multiple Sources (AAAI 2019 · similarity 0.87)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.87)
- Heuristic Domain Adaptation (NeurIPS 2020 · similarity 0.87)
- CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation (ICLR 2022 · similarity 0.87)
- COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation (ICML 2025 · similarity 0.85)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.85)
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.