Few-shot Image Classification with Multi-Facet Prototypes
This addresses the challenge of insufficient training examples in few-shot learning for image recognition, though it is incremental as it builds on existing metric-based methods.
The paper tackles few-shot image classification by organizing visual features into facets and predicting facet importance from category names, improving state-of-the-art results on miniImageNet and CUB datasets.
The aim of few-shot learning (FSL) is to learn how to recognize image categories from a small number of training examples. A central challenge is that the available training examples are normally insufficient to determine which visual features are most characteristic of the considered categories. To address this challenge, we organize these visual features into facets, which intuitively group features of the same kind (e.g. features that are relevant to shape, color, or texture). This is motivated from the assumption that (i) the importance of each facet differs from category to category and (ii) it is possible to predict facet importance from a pre-trained embedding of the category names. In particular, we propose an adaptive similarity measure, relying on predicted facet importance weights for a given set of categories. This measure can be used in combination with a wide array of existing metric-based methods. Experiments on miniImageNet and CUB show that our approach improves the state-of-the-art in metric-based FSL.