Research map / Label-efficient and robust learning / Domain adaptation and generalization
Implicit Task-Driven Probability Discrepancy Measure for Unsupervised Domain Adaptation
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 |
|---|---|---|---|
| replace joint optimization (vCDD) with bi-level implicit formulation (ablation) | CDD · Office-Home | accuracy (%): 69.3 -> 70.8 | Helped |
| replace joint optimization (vCDD) with bi-level implicit formulation (ablation) | CDD · Office-31 | accuracy (%): 90.6 -> 90.9 | Helped |
| replace joint optimization (vCDD) with bi-level implicit formulation (ablation) | CDD · ImageCLEF | accuracy (%): 88.9 -> 89.4 | Helped |
| replace standard MDD with implicit i-MDD | MDD · Office-31 | accuracy (%): 88.9 -> 89.4 | Helped |
| replace standard MDD with implicit i-MDD | MDD · Office-Home | accuracy (%): 68.1 -> 68.8 | Helped |
| replace standard MDD with implicit i-MDD | MDD · ImageCLEF | accuracy (%): 88.4 -> 88.4 | No clear effect |
| compute inter-class discrepancy on source only (vCDD) instead of source and target (ablation) | CDD · Office-Home | accuracy (%): 66.5 -> 69.3 | Helped |
| compute inter-class discrepancy on source only (vCDD) instead of source and target (ablation) | CDD · Office-31 | accuracy (%): 90.6 -> 90.6 | No clear effect |
| compute inter-class discrepancy on source only (vCDD) instead of source and target (ablation) | CDD · ImageCLEF | accuracy (%): 87.8 -> 88.9 | Helped |
| compare i-MDD against MDD+IA | i-MDD · Office-Home | accuracy (%): 69.5 -> 68.8 | Hurt |
| increase per-class cache size from 1 to 30, then beyond (ablation) | vCDD and i-CDD · Office-Home Ar:Cl | accuracy (%) | Mixed |
| increase latent dimensionality 128 to 1024 (ablation) | vCDD and i-CDD · Office-Home Ar:Cl | accuracy (%) | Helped |
Closest papers by meaning
- Unsupervised Domain Adaptation Based on Source-Guided Discrepancy (AAAI 2019 · similarity 0.91)
- On $f$-Divergence Principled Domain Adaptation: An Improved Framework (NeurIPS 2024 · similarity 0.88)
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.88)
- Unsupervised Domain Adaptation by Matching Distributions Based on the Maximum Mean Discrepancy via Unilateral Transformations (AAAI 2019 · similarity 0.88)
- Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.86)
- Efficient Discrepancy Testing for Learning with Distribution Shift (NeurIPS 2024 · 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.