Hierarchical Variational Memory for Few-shot Learning Across Domains
This addresses the challenge of domain shift in few-shot learning, which is crucial for real-world applications where training and test data differ, though it is an incremental improvement over existing memory models.
The paper tackled the problem of few-shot learning across domains by proposing a hierarchical variational memory that stores features at multiple semantic levels, achieving new state-of-the-art performance on cross-domain tasks and competitive results on traditional few-shot classification.
Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not generalize well in presence of a domain shift between training and test distributions. Rather than relying on a flat memory, we propose a hierarchical alternative that stores features at different semantic levels. We introduce a hierarchical prototype model, where each level of the prototype fetches corresponding information from the hierarchical memory. The model is endowed with the ability to flexibly rely on features at different semantic levels if the domain shift circumstances so demand. We meta-learn the model by a newly derived hierarchical variational inference framework, where hierarchical memory and prototypes are jointly optimized. To explore and exploit the importance of different semantic levels, we further propose to learn the weights associated with the prototype at each level in a data-driven way, which enables the model to adaptively choose the most generalizable features. We conduct thorough ablation studies to demonstrate the effectiveness of each component in our model. The new state-of-the-art performance on cross-domain and competitive performance on traditional few-shot classification further substantiates the benefit of hierarchical variational memory.