Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones. In contrast to both extremes, real world recognition problems exhibit heavy-tailed class distributions, with cluttered scenes and a mix of coarse and fine-grained class distinctions. We show that prior methods designed for few-shot learning do not work out of the box in these challenging conditions, based on a new "meta-iNat" benchmark. We introduce three parameter-free improvements: (a) better training procedures based on adapting cross-validation to meta-learning, (b) novel architectures that localize objects using limited bounding box annotations before classification, and (c) simple parameter-free expansions of the feature space based on bilinear pooling. Together, these improvements double the accuracy of state-of-the-art models on meta-iNat while generalizing to prior benchmarks, complex neural architectures, and settings with substantial domain shift.

介绍了三个无需参数的改进方案（a）基于将交叉验证适应到元学习的更好的训练流程，（b）使用有限的边界框注释来定位目标的新型架构，以及（c）基于双线性汇总的特征空间的简单无需参数的扩展，这些改进共同使得算法能够在真实世界的识别问题中表现更好。

现实场景下的带有区域定位的小样本学习