Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier
复制标题
少量图像分类：只需使用预先训练的特征提取器库和简单的分类器
DOI：
10.1109/iccv48922.2021.00931
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Jermaine, Chris
中科院分区：
文献类型：
--
作者：
Chowdhury, Arkabandhu;Jiang, Mingchao;Chaudhuri, Swarat;Jermaine, Chris
最近的论文表明，迁移学习可以在少量图像分类方面胜过复杂的元学习方法。我们把这个假设的逻辑结论，并建议使用一个高质量的，预先训练的特征提取器的合奏少拍图像分类。我们的实验表明，一个预先训练的特征提取器库与一个简单的前馈网络相结合，学习L2正则化可以是一个很好的选择，解决跨域少拍图像分类。我们的实验结果表明，这种更简单的样本效率方法远远优于几种成熟的元学习算法。
Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-trained feature extractors for few-shot image classification. We show experimentally that a library of pre-trained feature extractors combined with a simple feed-forward network learned with an L2-regularizer can be an excellent option for solving cross-domain few-shot image classification. Our experimental results suggest that this simpler sample-efficient approach far outperforms several well-established meta-learning algorithms.