arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.09338cs.CV
收藏

从多域表示中选择相关特征用于Few-Shot分类

Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification

Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔理工学院);LJK(朱尔·约瑟夫·李普曼实验室);École normale supérieure(巴黎高等师范学院);PSL Research Univ.(巴黎文理研究大学)

Nikita Dvornik, Cordelia Schmid, Julien Mairal

摘要:

Few-Shot分类的流行方法包括首先基于大型注释数据集学习通用数据表示,然后在仅给出几个标记样本的情况下将表示适应新类别。在这项工作中,我们提出了一个新的策略的基础上特征选择,这是既简单又有效的比以前的特征适应方法。首先,我们通过训练一组语义不同的特征提取器来获得多域表示。然后,给定一个少样本学习任务,我们使用我们的多域特征库自动选择最相关的表示。我们证明,基于这些特征构建的简单非参数分类器具有很高的准确性,并推广到训练过程中从未见过的领域,从而在MetaDataset上获得了最先进的结果,并提高了mini-ImageNet的准确性。

英文摘要:

Popular approaches for few-shot classification consist of first learning a generic data representation based on a large annotated dataset, before adapting the representation to new classes given only a few labeled samples. In this work, we propose a new strategy based on feature selection, which is both simpler and more effective than previous feature adaptation approaches. First, we obtain a multi-domain representation by training a set of semantically different feature extractors. Then, given a few-shot learning task, we use our multi-domain feature bank to automatically select the most relevant representations. We show that a simple non-parametric classifier built on top of such features produces high accuracy and generalizes to domains never seen during training, which leads to state-of-the-art results on MetaDataset and improved accuracy on mini-ImageNet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑