- Keywords: Meta-learning, few-shot learning, multi-domain
- TL;DR: We address multi-domain few-shot classification by building multiple models to represent this complex task distribution in a collective way and simplifying task-specific adaptation as a selection problem from these pre-trained models.
- Abstract: Although few-shot learning research has advanced rapidly with the help of meta-learning, its practical usefulness is still limited because most of the researches assumed that all meta-training and meta-testing examples came from a single domain. We propose a simple but effective way for few-shot classification in which a task distribution spans multiple domains including previously unseen ones during meta-training. The key idea is to build a pool of embedding models which have their own metric spaces and to learn to select the best one for a particular task through multi-domain meta-learning. This simplifies task-specific adaptation over a complex task distribution as a simple selection problem rather than modifying the model with a number of parameters at meta-testing time. Inspired by common multi-task learning techniques, we let all models in the pool share a base network and add a separate modulator to each model to refine the base network in its own way. This architecture allows the pool to maintain representational diversity and each model to have domain-invariant representation as well. Experiments show that our selection scheme outperforms other few-shot classification algorithms when target tasks could come from many different domains. They also reveal that aggregating outputs from all constituent models is effective for tasks from unseen domains showing the effectiveness of our framework.
- Code: https://drive.google.com/file/d/1FIP7lxc3bvM9kUoGbznLrEtKXqSxi4mo/view?usp=sharing