# Few-Shot Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/1711.02536 · HTML: https://mlsanity.com/paper/1711.02536/

## Key facts

- Cited by 111 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2017.

## Built on by (most cited first, 30 of 111)

- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Progressive Domain Expansion Network for Single Domain Generalization](https://mlsanity.com/paper/2103.16050/) (2021)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Domain Adaptation for Time Series Forecasting via Attention Sharing](https://mlsanity.com/paper/2102.06828/) (2021)
- [Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09415/) (2021)
- [Editing a classifier by rewriting its prediction rules](https://mlsanity.com/paper/2112.01008/) (2021)
- [Domain Adaptation for Time Series Under Feature and Label Shifts](https://mlsanity.com/paper/2302.03133/) (2023)
- [RDumb: A simple approach that questions our progress in continual test-time adaptation](https://mlsanity.com/paper/2306.05401/) (2023)
- [Uncertainty-guided Model Generalization to Unseen Domains](https://mlsanity.com/paper/2103.07531/) (2021)
- [Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing](https://mlsanity.com/paper/2203.12175/) (2022)
- [Non-IID data and Continual Learning processes in Federated Learning: A long road ahead](https://mlsanity.com/paper/2111.13394/) (2021)
- [Domain Generalization via Inference-time Label-Preserving Target Projections](https://mlsanity.com/paper/2103.01134/) (2021)
- [One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models](https://mlsanity.com/paper/2303.18080/) (2023)
- [Using Language to Extend to Unseen Domains](https://mlsanity.com/paper/2210.09520/) (2022)
- [Progressive Random Convolutions for Single Domain Generalization](https://mlsanity.com/paper/2304.00424/) (2023)
- [Collaborating Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.09788/) (2023)
- [Cross-Lingual Abstractive Summarization with Limited Parallel Resources](https://mlsanity.com/paper/2105.13648/) (2021)
- [Learning to Generalize across Domains on Single Test Samples](https://mlsanity.com/paper/2202.08045/) (2022)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations](https://mlsanity.com/paper/2401.05792/) (2024)
- [Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach](https://mlsanity.com/paper/2108.02888/) (2021)
- [Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data](https://mlsanity.com/paper/2109.06486/) (2021)
- [When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations](https://mlsanity.com/paper/2308.04431/) (2023)
- [TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2106.06326/) (2021)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2110.11650/) (2021)
- [Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts](https://mlsanity.com/paper/2106.00322/) (2021)
- [Few-Shot Domain Adaptation with Polymorphic Transformers](https://mlsanity.com/paper/2107.04805/) (2021)

## Abstract (arXiv)

This work provides a framework for addressing the problem of supervised domain adaptation with deep models. The main idea is to exploit adversarial learning to learn an embedded subspace that simultaneously maximizes the confusion between two domains while semantically aligning their embedding. The supervised setting becomes attractive especially when there are only a few target data samples that need to be labeled. In this few-shot learning scenario, alignment and separation of semantic probability distributions is difficult because of the lack of data. We found that by carefully designing a training scheme whereby the typical binary adversarial discriminator is augmented to distinguish between four different classes, it is possible to effectively address the supervised adaptation problem. In addition, the approach has a high speed of adaptation, i.e. it requires an extremely low number of labeled target training samples, even one per category can be effective. We then extensively compare this approach to the state of the art in domain adaptation in two experiments: one using datasets for handwritten digit recognition, and one using datasets for visual object recognition.