Learning to Select Base Classes for Few-shot Classification
This addresses a previously unexplored issue in few-shot learning for researchers, though it is incremental as it builds on existing methods.
The paper tackles the problem of selecting base classes for few-shot classification, showing that using a Similarity Ratio measure and submodular optimization leads to better base datasets, with experiments on ImageNet, Caltech256, and CUB-200-2011 demonstrating effectiveness.
Few-shot learning has attracted intensive research attention in recent years. Many methods have been proposed to generalize a model learned from provided base classes to novel classes, but no previous work studies how to select base classes, or even whether different base classes will result in different generalization performance of the learned model. In this paper, we utilize a simple yet effective measure, the Similarity Ratio, as an indicator for the generalization performance of a few-shot model. We then formulate the base class selection problem as a submodular optimization problem over Similarity Ratio. We further provide theoretical analysis on the optimization lower bound of different optimization methods, which could be used to identify the most appropriate algorithm for different experimental settings. The extensive experiments on ImageNet, Caltech256 and CUB-200-2011 demonstrate that our proposed method is effective in selecting a better base dataset.