arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.01339cs.LG
收藏

基于领域相似度和Few-Shot难度的跨领域少样本学习

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

KAIST(韩国科学技术院);NAVER AI Lab(NAVER人工智能实验室);SNU AIIS(首尔大学人工智能研究所)

Jaehoon Oh, Sungnyun Kim, Namgyu Ho, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun

摘要:

跨域少样本学习(CD-FSL)在处理源域和目标域之间的巨大差异方面引起了越来越多的关注-这是现实世界场景中的一个重要问题。为了克服这些巨大的差异,最近的工作已经考虑在预训练阶段利用来自目标域的小规模未标记数据。除了在源域上进行有监督的预训练之外,这些数据还可以在目标域上进行自我监督的预训练。在本文中,我们经验性地研究了基于领域相似性和目标领域的Few-Shot难度的预训练。我们发现,当目标域与源域不相似或目标域本身具有低Few-Shot难度时,自监督预训练的性能增益比监督预训练大。我们进一步设计了两个预训练方案,混合监督和两阶段学习,提高性能。在这种情况下,我们提出了六个研究结果的CD-FSL,这是支持广泛的实验和分析的三个源和八个目标基准数据集不同程度的域相似性和Few-Shot的难度。我们的代码可在https://github.com/sungnyun/understanding-cdfsl上获得。

英文摘要:

Cross-domain few-shot learning (CD-FSL) has drawn increasing attention for handling large differences between the source and target domains--an important concern in real-world scenarios. To overcome these large differences, recent works have considered exploiting small-scale unlabeled data from the target domain during the pre-training stage. This data enables self-supervised pre-training on the target domain, in addition to supervised pre-training on the source domain. In this paper, we empirically investigate which pre-training is preferred based on domain similarity and few-shot difficulty of the target domain. We discover that the performance gain of self-supervised pre-training over supervised pre-training becomes large when the target domain is dissimilar to the source domain, or the target domain itself has low few-shot difficulty. We further design two pre-training schemes, mixed-supervised and two-stage learning, that improve performance. In this light, we present six findings for CD-FSL, which are supported by extensive experiments and analyses on three source and eight target benchmark datasets with varying levels of domain similarity and few-shot difficulty. Our code is available at https://github.com/sungnyun/understanding-cdfsl.

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。

↑