Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Domain Adaptation With Distribution Matching Machines
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 instance reweighting to feature matching (ablation) | DMMA · Office10-Caltech10 DeCAF6 | accuracy: 87.4 -> 89.4 | Helped |
| add instance reweighting to feature matching (ablation) | DMMA · Office10-Caltech10 DeCAF7 | accuracy: 89.4 -> 91.6 | Helped |
| add instance reweighting to feature matching (ablation) | DMMA · Reuters-21578 | accuracy: 76.1 -> 76.8 | Helped |
| joint end-to-end training instead of two-step (ablation) | DMM2 · Office10-Caltech10 DeCAF6 | accuracy: 88.8 -> 89.4 | Helped |
| joint end-to-end training instead of two-step (ablation) | DMM2 · Reuters-21578 | accuracy: 75.5 -> 76.8 | Helped |
| DMM vs best baseline LSSA | domain adaptation · Office10-Caltech10 DeCAF6 | accuracy: 85.5 -> 89.4 | Helped |
| instance reweighting only (KMM) vs SVM | SVM · Office10-Caltech10 DeCAF6 | accuracy: 82.0 -> 82.2 | No clear effect |
Closest papers by meaning
- Unsupervised Domain Adaptation by Matching Distributions Based on the Maximum Mean Discrepancy via Unilateral Transformations (AAAI 2019 · similarity 0.91)
- Exploiting Local Feature Patterns for Unsupervised Domain Adaptation (AAAI 2019 · similarity 0.90)
- Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss (CVPR 2019 · similarity 0.90)
- Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.89)
- Unsupervised Domain Adaptation With Similarity Learning (CVPR 2018 · similarity 0.89)
- Learning Transferrable Representations for Unsupervised Domain Adaptation (NeurIPS 2016 · 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.