arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09467cs.CV
收藏

基于张量幻觉的少样本学习

Few-shot learning via tensor hallucination

Imperial College London(帝国理工学院);Inria, Univ Rennes, CNRS, IRISA(法国国家信息与自动化研究所,雷恩大学,法国国家科学研究中心,IRISA)

Michalis Lazarou, Yannis Avrithis, Tania Stathaki

摘要:

Few-Shot分类解决了仅给定有限标记数据的分类示例的挑战。一个强有力的方法是超越数据增强,走向数据综合。然而,大多数用于Few-Shot分类的数据增强/合成方法过于复杂和复杂,例如,用多个正则化器训练wGAN或训练网络以将潜在的差异从已知类别转移到新类别。我们做了两个贡献,即我们表明:(1)使用一个简单的损失函数是足够的训练特征生成器在Few-Shot设置;(2)学习生成张量特征,而不是矢量特征是优越的。在miniImagenet、CUB和CIFAR-FS数据集上的大量实验表明,我们的方法开创了一个新的领域,优于更复杂的Few-Shot数据增强方法。

英文摘要:

Few-shot classification addresses the challenge of classifying examples given only limited labeled data. A powerful approach is to go beyond data augmentation, towards data synthesis. However, most of data augmentation/synthesis methods for few-shot classification are overly complex and sophisticated, e.g. training a wGAN with multiple regularizers or training a network to transfer latent diversities from known to novel classes. We make two contributions, namely we show that: (1) using a simple loss function is more than enough for training a feature generator in the few-shot setting; and (2) learning to generate tensor features instead of vector features is superior. Extensive experiments on miniImagenet, CUB and CIFAR-FS datasets show that our method sets a new state of the art, outperforming more sophisticated few-shot data augmentation methods.

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。

↑