Research map / Label-efficient and robust learning / Domain adaptation and generalization
Representation Subspace Distance for Domain Adaptation Regression
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 RSD + BMP (full method) versus source-only ResNet-18 | domain adaptation regression · dSprites | sum MAE avg over 6 tasks: 0.498 -> 0.237 | Helped |
| add BMP regularizer on top of RSD (ablation) | RSD · dSprites | sum MAE avg: 0.258 -> 0.237 | Helped |
| add BMP regularizer on top of RSD (ablation) | RSD · MPI3D | sum MAE avg: 0.242 -> 0.205 | Helped |
| add BMP regularizer on top of RSD (ablation) | RSD · Biwi Kinect | sum MAE: F->M 0.33 -> 0.30; M->F 0.27 -> 0.26 | Helped |
| RSD+BMP versus source-only ResNet-18 | domain adaptation regression · MPI3D | sum MAE avg over 6 tasks: 0.377 -> 0.205 | Helped |
| RSD+BMP versus source-only ResNet-18 | domain adaptation regression · Biwi Kinect | sum MAE: F->M 0.38 -> 0.30; M->F 0.29 -> 0.26 | Helped |
| adopt standard DAC deep adaptation methods (DANN, DAN, MCD, AFN, JDOT) for regression | domain adaptation regression · dSprites | sum MAE avg: DANN 0.315 and DAN 0.377 improve on 0.498; AFN 0.523 and TCA 0.498 do not improve | Mixed |
| adopt standard DAC deep adaptation methods for regression | domain adaptation regression · Biwi Kinect | sum MAE: DAN 0.37/0.28 improves slightly; AFN 0.41/0.32 and MCD/DANN/JDOT worse than or equal to source-only on some tasks | Mixed |
| adopt AFN (adaptive feature norm) for regression | domain adaptation regression · MPI3D | sum MAE avg: 0.377 -> 0.390 | Hurt |
| adopt AFN (adaptive feature norm) for regression | domain adaptation regression · dSprites | sum MAE avg: 0.498 -> 0.523 | Hurt |
Closest papers by meaning
- Learning an Invariant Hilbert Space for Domain Adaptation (CVPR 2017 · similarity 0.90)
- Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? (NeurIPS 2021 · similarity 0.89)
- Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment (AAAI 2020 · similarity 0.89)
- StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold (NeurIPS 2025 · similarity 0.87)
- Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.86)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.86)
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.