# Zero Shot Domain Generalization

arXiv: https://arxiv.org/abs/2008.07443 · HTML: https://mlsanity.com/paper/2008.07443/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2020.

## Built on by (most cited first, 12 of 12)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Anomaly Detection under Distribution Shift](https://mlsanity.com/paper/2303.13845/) (2023)
- [Domain-Unified Prompt Representations for Source-Free Domain Generalization](https://mlsanity.com/paper/2209.14926/) (2022)
- [Handling Out-of-Distribution Data: A Survey](https://mlsanity.com/paper/2507.21160/) (2025)
- [Tackling Long-Tailed Category Distribution Under Domain Shifts](https://mlsanity.com/paper/2207.10150/) (2022)
- [Universal Cross-Domain Retrieval: Generalizing Across Classes and Domains](https://mlsanity.com/paper/2108.08356/) (2021)
- [Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains](https://mlsanity.com/paper/2107.07497/) (2021)
- [A separability-based approach to quantifying generalization: which layer is best?](https://mlsanity.com/paper/2405.01524/) (2024)
- [Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains](https://mlsanity.com/paper/2107.05622/) (2021)
- [Reappraising Domain Generalization in Neural Networks](https://mlsanity.com/paper/2110.07981/) (2021)
- [INDIGO: Intrinsic Multimodality for Domain Generalization](https://mlsanity.com/paper/2206.05912/) (2022)

## Abstract (arXiv)

Standard supervised learning setting assumes that training data and test data come from the same distribution (domain). Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would generalize to a new unseen domain. We extend DG to an even more challenging setting, where the label space of the unseen domain could also change. We introduce this problem as Zero-Shot Domain Generalization (to the best of our knowledge, the first such effort), where the model generalizes across new domains and also across new classes in those domains. We propose a simple strategy which effectively exploits semantic information of classes, to adapt existing DG methods to meet the demands of Zero-Shot Domain Generalization. We evaluate the proposed methods on CIFAR-10, CIFAR-100, F-MNIST and PACS datasets, establishing a strong baseline to foster interest in this new research direction.