Research map / Learning theory and algorithms / Optimal transport
Unbalanced minibatch Optimal Transport; applications to 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 |
|---|---|---|---|
| Use minibatch unbalanced OT instead of minibatch balanced OT | domain adaptation with JUMBOT · Office-Home UDA (12 tasks) | average accuracy: 66.6 -> 70.0 | Helped |
| Use minibatch unbalanced OT instead of minibatch balanced OT | domain adaptation with JUMBOT · Office-Home PDA (12 tasks) | average accuracy: 60.9 -> 75.5 | Helped |
| Use minibatch unbalanced OT instead of minibatch balanced OT | domain adaptation with JUMBOT · Digits UDA (U→M, M→MM, S→M) | average accuracy: 94.5 -> 98.0 | Helped |
| Use minibatch unbalanced OT instead of minibatch balanced OT | domain adaptation with JUMBOT · VisDA-2017 validation | accuracy: +2% | Helped |
| Relax minibatch transport marginal constraints | minibatch OT transport plans · 2D imbalanced-cluster example | cross-class pairings | Helped |
| Use minibatch unbalanced OT rather than minibatch OT | gradient flow on imbalanced 2D clusters · 2D gradient-flow example | target-shape preservation | Helped |
| Replace minibatch balanced OT with minibatch unbalanced OT | USPS-to-MNIST transfer connections · USPS→MNIST | mass on different-label connections: 7% -> 0.7% | Helped |
Closest papers by meaning
- Unbalanced CO-optimal Transport (AAAI 2023 · similarity 0.91)
- Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport (NeurIPS 2023 · similarity 0.89)
- Incorporating Importance Weighting in Optimal Transport Based Domain Alignment (ICML 2026 · similarity 0.89)
- Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.88)
- Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport (NeurIPS 2026 · similarity 0.87)
- Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation (ICLR 2024 · similarity 0.87)
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.