Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- February 2020
- DOI:
- 10.48550/arXiv.2002.02050
- arXiv:
- arXiv:2002.02050
- Bibcode:
- 2020arXiv200202050G
- Keywords:
-
- Computer Science - Machine Learning;
- Statistics - Machine Learning
- E-Print:
- There exist some mistakes in the experiments