We propose unsupervised embedding adaptation for the downstream few-shot classification task. Based on findings that deep neural networks learn to generalize before memorizing, we develop Early-Stage Feature Reconstruction (ESFR) -- a novel adaptation scheme with feature reconstruction and dimensionality-driven early stopping that finds generalizable features. Incorporating ESFR consistently improves the performance of baseline methods on all standard settings, including the recently proposed transductive method. ESFR used in conjunction with the transductive method further achieves state-of-the-art performance on mini-ImageNet, tiered-ImageNet, and CUB; especially with 1.2%~2.0% improvements in accuracy over the previous best performing method on 1-shot setting.
翻译:我们建议为下游的微小分类任务不受监督地嵌入适应。根据深神经网络在记忆化前学会了普及化的研究结果,我们开发了早期功能重建(ESFR) -- -- 这是一种具有特征重建和维度驱动的早期停止的新适应计划,具有可概括的特征。纳入ESFR会不断改善所有标准设置基准方法的性能,包括最近提议的转导方法。与传输方法一起使用的ESFR进一步实现了微型-IMageNet、分级-IMageNet和CUB的先进性能;特别是比以往1集式最佳性能方法的准确性能提高了1.2 ⁇ 2.0%。