Research map / Label-efficient and robust learning / Domain adaptation and generalization

Optimization-based domain generalization

Studies failure modes and gradient-guided or meta-learning methods for domain generalization.

101 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in Domain adaptation and generalization, keyword cluster “domain generalization · dg · unseen”

State History Benchmarks Tried Baselines Checklist Preprints Who Export

How it got here

Most cited paper of each year

• 2018 · Domain Generalization With Adversarial Feature Learning (CVPR 2018 · 1,271 citations)
• 2019 · Domain Generalization by Solving Jigsaw Puzzles (CVPR 2019 · 862 citations)
• 2020 · Learning to Learn Single Domain Generalization (CVPR 2020 · 468 citations)
• 2021 · A Fourier-Based Framework for Domain Generalization (CVPR 2021 · 561 citations)
• 2022 · PCL: Proxy-Based Contrastive Learning for Domain Generalization (CVPR 2022 · 133 citations)
• 2023 · Deep Frequency Filtering for Domain Generalization (CVPR 2023 · 93 citations)
• 2024 · Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · 30 citations)
• 2025 · Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization (CVPR 2025 · 5 citations)
• 2026 · MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment (AAAI 2026 · 1 citation)

Earliest papers here

• Domain Generalization With Adversarial Feature Learning (CVPR 2018 · 1,271 citations)
• Learning to Generalize: Meta-Learning for Domain Generalization (AAAI 2018 · 1,265 citations)
• MetaReg: Towards Domain Generalization using Meta-Regularization (NeurIPS 2018 · 391 citations)

Benchmark records

The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.

What has been tried

80 papers here report 903 measured changes (a component added, removed or swapped, compared with a baseline): helped 69%, no clear effect 7%, hurt 20%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

Baseline numbers that disagree

The same baseline on the same benchmark and metric, reported more than 5% apart by different papers here. Training budgets, data splits and reimplementations differ, so state which number you compare with.

What reviewers will expect

Datasets and baselines named in the 15 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.

Recent preprints

Who publishes on it

Institutions on the most papers of this approach since 2023 (of 56 papers; from OpenAlex and the papers' affiliations).

• Huawei · 2 papers
• Beihang University · 2 papers
• University of Western Ontario · 2 papers
• The Chinese University of Hong Kong · 2 papers
• Columbia University · 2 papers
• Indian Institute of Technology · 2 papers
• University of Science and Technology of China · 2 papers
• Microsoft · 2 papers
• Shanghai Jiao Tong University · 2 papers
• Beijing Institute of Technology · 2 papers

Use it

Download BibTeX of 40 key papersOpen the topic in the interactive map

Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.

Related approaches

Same keyword cluster

• Foundation-model domain generalization (56 papers)
• Augmentation and mixture-of-experts generalization (51 papers)
• Generalizable person re-identification (11 papers)

Elsewhere in the topic

• Conditional distribution alignment (162 papers)
• Cross-domain few-shot with transformers (116 papers)
• Feature alignment for unsupervised adaptation (105 papers)
• Adversarial domain adaptation (95 papers)
• Geometric alignment and synthetic-to-real adaptation (93 papers)
• Source-free domain adaptation (92 papers)
• Adaptation for semantic segmentation (81 papers)
• Statistical alignment and hypothesis testing (80 papers)

Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).