Research map / Label-efficient and robust learning / Domain adaptation and generalization
MVDG: A Unified Multi-View Framework for Domain Generalization
Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 multi-view regularized meta-learning (MVRML) (ablation) | ResNet-18 DeepAll · PACS | accuracy (%): 79.21 -> 85.89 | Improved |
| add MVRML (ablation) | ResNet-50 DeepAll · PACS | accuracy (%): 84.37 -> 88.95 | Improved |
| add multi-view prediction (MVP) on top of MVRML (ablation) | MVRML ResNet-18 · PACS | accuracy (%): 85.89 -> 86.56 | Improved |
| add MVP on top of MVRML (ablation) | MVRML ResNet-50 · PACS | accuracy (%): 88.95 -> 89.33 | Improved |
| use MVRML instead of Reptile (ablation) | ResNet-18 meta-learning · PACS | accuracy (%): 82.34 -> 85.89 | Improved |
| train Reptile baseline versus DeepAll (ablation) | ResNet-18 · PACS | accuracy (%): 79.21 -> 82.34 | Improved |
| sample tasks from random split meta-domains (S3) rather than same domain (S1) (ablation) | MVRML · PACS | accuracy (%): 84.27 -> 85.89 | Improved |
| sample tasks from random split meta-domains (S3) rather than all domains (S2) (ablation) | MVRML · PACS | accuracy (%): 84.82 -> 85.89 | Improved |
| add MVP to MixStyle | MixStyle · PACS | accuracy (%): 82.81 -> 84.49 | Improved |
| add MVP to RSC | RSC · PACS | accuracy (%): 84.96 -> 85.49 | Improved |
| add MVP to FSR | FSR · PACS | accuracy (%): 85.90 -> 86.76 | Improved |
| add RandAugment to MVP augmentations (ablation) | MVRML + MVP · PACS | accuracy (%): 86.24 -> 79.00 | Hurt |
Later papers that compared with this method
1 later accepted paper reports MVDG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization (ICCV 2023 · better on 4 of 5 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SWAD — SWAD: Domain Generalization by Seeking Flat Minima (NeurIPS 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization (CVPR 2024 · similarity 0.89)
- Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · similarity 0.89)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.88)
- One-Step Generalization Ratio Guided Optimization for Domain Generalization (ICML 2025 · similarity 0.88)
- Is Large-scale Pretraining the Secret to Good Domain Generalization? (ICLR 2025 · similarity 0.87)
- Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap (ICLR 2025 · 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.
