arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00315cs.CVcs.LGstat.ML
收藏

学习选择用于Few-Shot分类的基类

Learning to Select Base Classes for Few-shot Classification

Tsinghua University(清华大学);Noah’s Ark Lab, Huawei Technologies(华为技术有限公司诺亚方舟实验室)

Linjun Zhou, Peng Cui, Xu Jia, Shiqiang Yang, Qi Tian

摘要:

近年来,少样本学习引起了广泛的研究关注。已经提出了许多方法来将从提供的基类学习到的模型推广到新的类,但是以前的工作没有研究如何选择基类,或者甚至不同的基类是否会导致学习模型的不同推广性能。在本文中,我们利用一个简单而有效的措施,相似比,作为一个指标的泛化性能的Few-Shot模型。然后,我们制定的基类选择问题作为一个子模块的相似比优化问题。进一步对不同优化方法的优化下界进行了理论分析,为不同的实验设置确定最合适的算法。在ImageNet、Caltech 256和CUB-200-2011上的大量实验表明,该方法在选择更好的基础数据集方面是有效的。

英文摘要:

Few-shot learning has attracted intensive research attention in recent years. Many methods have been proposed to generalize a model learned from provided base classes to novel classes, but no previous work studies how to select base classes, or even whether different base classes will result in different generalization performance of the learned model. In this paper, we utilize a simple yet effective measure, the Similarity Ratio, as an indicator for the generalization performance of a few-shot model. We then formulate the base class selection problem as a submodular optimization problem over Similarity Ratio. We further provide theoretical analysis on the optimization lower bound of different optimization methods, which could be used to identify the most appropriate algorithm for different experimental settings. The extensive experiments on ImageNet, Caltech256 and CUB-200-2011 demonstrate that our proposed method is effective in selecting a better base dataset.

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。

↑