# Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2007.09257 · HTML: https://mlsanity.com/paper/2007.09257/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 24 of 24)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization](https://mlsanity.com/paper/2201.06910/) (2022)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Wasserstein Task Embedding for Measuring Task Similarities](https://mlsanity.com/paper/2208.11726/) (2022)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.09988/) (2022)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data](https://mlsanity.com/paper/2412.06284/) (2024)
- [Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation](https://mlsanity.com/paper/2302.02561/) (2023)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Graph-Relational Domain Adaptation](https://mlsanity.com/paper/2202.03628/) (2022)
- [Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement](https://mlsanity.com/paper/2201.01929/) (2022)
- [A Bag-of-Prototypes Representation for Dataset-Level Applications](https://mlsanity.com/paper/2303.13251/) (2023)
- [Cyclically Disentangled Feature Translation for Face Anti-spoofing](https://mlsanity.com/paper/2212.03651/) (2022)
- [Taxonomy-Structured Domain Adaptation](https://mlsanity.com/paper/2306.07874/) (2023)
- [Domain Attention Consistency for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2111.03911/) (2021)
- [Distilling from Similar Tasks for Transfer Learning on a Budget](https://mlsanity.com/paper/2304.12314/) (2023)
- [Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain Detection](https://mlsanity.com/paper/2106.03496/) (2021)
- [Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies](https://mlsanity.com/paper/2505.22829/) (2025)
- [Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replay](https://mlsanity.com/paper/2402.00580/) (2024)
- [Clone-Robust Weights in Metric Spaces: Handling Redundancy Bias for Benchmark Aggregation](https://mlsanity.com/paper/2502.03576/) (2025)
- [LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2505.19659/) (2025)
- [DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution](https://mlsanity.com/paper/2606.18307/) (2026)
- [Learning Embeddings for Sequential Tasks Using Population of Agents](https://mlsanity.com/paper/2306.03311/) (2023)

## Abstract (arXiv)

Conventional unsupervised domain adaptation (UDA) studies the knowledge transfer between a limited number of domains. This neglects the more practical scenario where data are distributed in numerous different domains in the real world. The domain similarity between those domains is critical for domain adaptation performance. To describe and learn relations between different domains, we propose a novel Domain2Vec model to provide vectorial representations of visual domains based on joint learning of feature disentanglement and Gram matrix. To evaluate the effectiveness of our Domain2Vec model, we create two large-scale cross-domain benchmarks. The first one is TinyDA, which contains 54 domains and about one million MNIST-style images. The second benchmark is DomainBank, which is collected from 56 existing vision datasets. We demonstrate that our embedding is capable of predicting domain similarities that match our intuition about visual relations between different domains. Extensive experiments are conducted to demonstrate the power of our new datasets in benchmarking state-of-the-art multi-source domain adaptation methods, as well as the advantage of our proposed model.