# Few-Shot Learning as Domain Adaptation: Algorithm and Analysis

arXiv: https://arxiv.org/abs/2002.02050 · HTML: https://mlsanity.com/paper/2002.02050/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2020.

## Built on by (most cited first, 4 of 4)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Combat Data Shift in Few-shot Learning with Knowledge Graph](https://mlsanity.com/paper/2101.11354/) (2021)
- [Joint Text and Label Generation for Spoken Language Understanding](https://mlsanity.com/paper/2105.05052/) (2021)
- [Proposal Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2606.09245/) (2026)

## Abstract (arXiv)

To recognize the unseen classes with only few samples, few-shot learning (FSL) uses prior knowledge learned from the seen classes. A major challenge for FSL is that the distribution of the unseen classes is different from that of those seen, resulting in poor generalization even when a model is meta-trained on the seen classes. This class-difference-caused distribution shift can be considered as a special case of domain shift. In this paper, for the first time, we propose a domain adaptation prototypical network with attention (DAPNA) to explicitly tackle such a domain shift problem in a meta-learning framework. Specifically, armed with a set transformer based attention module, we construct each episode with two sub-episodes without class overlap on the seen classes to simulate the domain shift between the seen and unseen classes. To align the feature distributions of the two sub-episodes with limited training samples, a feature transfer network is employed together with a margin disparity discrepancy (MDD) loss. Importantly, theoretical analysis is provided to give the learning bound of our DAPNA. Extensive experiments show that our DAPNA outperforms the state-of-the-art FSL alternatives, often by significant margins.