Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning an Invariant Hilbert Space for 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 |
|---|---|---|---|
| Jointly learn source and target projections and a latent Mahalanobis metric while matching projected domain covariances | ILS · Office+Caltech10 semi-supervised domain adaptation | accuracy | Helped |
| Jointly learn projections and covariance matching for domain alignment | ILS · Office+Caltech10 unsupervised domain adaptation | accuracy | Helped |
| Use the ILS-learned source transformation instead of PCA subspaces for GFK and SA | GFK and SA · Office-Caltech | accuracy | Helped |
| Set the statistical-loss weight λ to zero, removing statistical matching (ablation) | ILS · Office+Caltech10 unsupervised VGG-FC6 | accuracy | Hurt |
| Vary λ among nonzero values (ablation) | ILS · Office+Caltech10 unsupervised VGG-FC6 | accuracy | No clear effect |
| Remove the orthogonality constraints on the source and target projections (ablation) | ILS · Domain adaptation | accuracy | Hurt |
| Use product-manifold optimization rather than alternating Riemannian optimization (ablation) | ILS optimization · Optimization objective | loss | Mixed |
Closest papers by meaning
- LEARNING FACTORIZED REPRESENTATIONS FOR OPEN-SET DOMAIN ADAPTATION (ICLR 2019 · similarity 0.91)
- Visual Domain Adaptation by Consensus-Based Transfer to Intermediate Domain (AAAI 2020 · similarity 0.91)
- Multivariate Regression on the Grassmannian for Predicting Novel Domains (CVPR 2016 · similarity 0.90)
- Heuristic Domain Adaptation (NeurIPS 2020 · similarity 0.90)
- Representation Subspace Distance for Domain Adaptation Regression (ICML 2021 · similarity 0.90)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 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.