# Adaptive Methods for Real-World Domain Generalization

arXiv: https://arxiv.org/abs/2103.15796 · HTML: https://mlsanity.com/paper/2103.15796/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Kernel Mean Embedding of Distributions: A Review and Beyond](https://mlsanity.com/paper/1605.09522/) (2016)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [Domain Generalization for Object Recognition with Multi-task Autoencoders](https://mlsanity.com/paper/1508.07680/) (2015)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Improve Unsupervised Domain Adaptation with Mixup Training](https://mlsanity.com/paper/2001.00677/) (2020)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)
- [Domain Generalization via Conditional Invariant Representation](https://mlsanity.com/paper/1807.08479/) (2018)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [Regularized Learning for Domain Adaptation under Label Shifts](https://mlsanity.com/paper/1903.09734/) (2019)
- [Range Loss for Deep Face Recognition with Long-tail](https://mlsanity.com/paper/1611.08976/) (2016)
- [Heterogeneous Domain Generalization via Domain Mixup](https://mlsanity.com/paper/2009.05448/) (2020)

## Built on by (most cited first, 30 of 66)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.03721/) (2021)
- [Extending the WILDS Benchmark for Unsupervised Adaptation](https://mlsanity.com/paper/2112.05090/) (2021)
- [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https://mlsanity.com/paper/2309.12659/) (2023)
- [Back to the Source: Diffusion-Driven Test-Time Adaptation](https://mlsanity.com/paper/2207.03442/) (2022)
- [Probable Domain Generalization via Quantile Risk Minimization](https://mlsanity.com/paper/2207.09944/) (2022)
- [GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition](https://mlsanity.com/paper/2301.02560/) (2023)
- [AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation](https://mlsanity.com/paper/2304.12566/) (2023)
- [Semi-Supervised Domain Generalization with Stochastic StyleMatch](https://mlsanity.com/paper/2106.00592/) (2021)
- [V-IRL: Grounding Virtual Intelligence in Real Life](https://mlsanity.com/paper/2402.03310/) (2024)
- [Learning to Generalize across Domains on Single Test Samples](https://mlsanity.com/paper/2202.08045/) (2022)
- [Any-Shift Prompting for Generalization over Distributions](https://mlsanity.com/paper/2402.10099/) (2024)
- [Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition](https://mlsanity.com/paper/2310.18562/) (2023)
- [GeoNet: Benchmarking Unsupervised Adaptation across Geographies](https://mlsanity.com/paper/2303.15443/) (2023)
- [Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation](https://mlsanity.com/paper/2308.14023/) (2023)
- [No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models](https://mlsanity.com/paper/2405.13777/) (2024)
- [Label-Efficient Domain Generalization via Collaborative Exploration and Generalization](https://mlsanity.com/paper/2208.03644/) (2022)
- [Domain-Specific Risk Minimization for Out-of-Distribution Generalization](https://mlsanity.com/paper/2208.08661/) (2022)
- [Energy-Based Test Sample Adaptation for Domain Generalization](https://mlsanity.com/paper/2302.11215/) (2023)
- [Learning Instance-Specific Adaptation for Cross-Domain Segmentation](https://mlsanity.com/paper/2203.16530/) (2022)
- [Prefix Conditioning Unifies Language and Label Supervision](https://mlsanity.com/paper/2206.01125/) (2022)
- [DEJA VU: Continual Model Generalization For Unseen Domains](https://mlsanity.com/paper/2301.10418/) (2023)
- [Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?](https://mlsanity.com/paper/2307.13136/) (2023)
- [Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models](https://mlsanity.com/paper/2311.05746/) (2023)
- [Adaptive Domain Generalization via Online Disagreement Minimization](https://mlsanity.com/paper/2208.01996/) (2022)
- [Activate and Reject: Towards Safe Domain Generalization under Category Shift](https://mlsanity.com/paper/2310.04724/) (2023)
- [Model-free Test Time Adaptation for Out-Of-Distribution Detection](https://mlsanity.com/paper/2311.16420/) (2023)
- [Can domain adaptation make object recognition work for everyone?](https://mlsanity.com/paper/2204.11122/) (2022)
- [Aggregation of Disentanglement: Reconsidering Domain Variations in Domain Generalization](https://mlsanity.com/paper/2302.02350/) (2023)

## Abstract (arXiv)

Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate whether it is possible to leverage domain information from the unseen test samples themselves. We propose a domain-adaptive approach consisting of two steps: a) we first learn a discriminative domain embedding from unsupervised training examples, and b) use this domain embedding as supplementary information to build a domain-adaptive model, that takes both the input as well as its domain into account while making predictions. For unseen domains, our method simply uses few unlabelled test examples to construct the domain embedding. This enables adaptive classification on any unseen domain. Our approach achieves state-of-the-art performance on various domain generalization benchmarks. In addition, we introduce the first real-world, large-scale domain generalization benchmark, Geo-YFCC, containing 1.1M samples over 40 training, 7 validation, and 15 test domains, orders of magnitude larger than prior work. We show that the existing approaches either do not scale to this dataset or underperform compared to the simple baseline of training a model on the union of data from all training domains. In contrast, our approach achieves a significant improvement.