A Closer Look at Few-shot Classification
This work addresses the challenge of evaluating few-shot learning algorithms for researchers, providing insights into method comparisons and cross-domain generalization, though it is incremental in nature.
The paper tackled the problem of fair comparison in few-shot classification by conducting a consistent analysis, showing that deeper backbones reduce performance differences among methods and that a modified baseline achieves competitive results on datasets like miniImageNet and CUB.
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difficult. In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the performance differences among methods on datasets with limited domain differences, 2) a modified baseline method that surprisingly achieves competitive performance when compared with the state-of-the-art on both the \miniI and the CUB datasets, and 3) a new experimental setting for evaluating the cross-domain generalization ability for few-shot classification algorithms. Our results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones. In a realistic cross-domain evaluation setting, we show that a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms.