arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.04232cs.CV
收藏

Few-Shot分类的深入研究

A Closer Look at Few-shot Classification

Carnegie Mellon University(卡内基梅隆大学);Georgia Tech(佐治亚理工学院);National Taiwan University(国立台湾大学);Virginia Tech(弗吉尼亚理工学院)

Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, Jia-Bin Huang

摘要:

Few-Shot分类的目标是学习一个分类器,以识别在训练过程中使用有限的标记样本的不可见类。虽然已经取得了重大进展,但网络设计、Meta学习算法和实现细节差异的日益复杂性使得很难进行公平的比较。在本文中,我们提出了1)几个代表性的Few-Shot分类算法的一致比较分析,结果表明,更深的主干显着减少了有限域差异数据集上方法之间的性能差异,2)一个修改的基线方法,与\miniI和CUB数据集上的最新技术相比,令人惊讶地实现了具有竞争力的性能,3)为评价Few-Shot分类算法的跨领域泛化能力提供了一种新的实验环境。我们的研究结果表明,减少类内变化是一个重要的因素时,功能骨干是浅,但不是关键时,使用更深的骨干。在一个现实的跨域评估设置,我们表明,一个标准的微调做法的基线方法相比,优于其他国家的最先进的少样本学习算法。

英文摘要:

Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difficult. In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the performance differences among methods on datasets with limited domain differences, 2) a modified baseline method that surprisingly achieves competitive performance when compared with the state-of-the-art on both the \miniI and the CUB datasets, and 3) a new experimental setting for evaluating the cross-domain generalization ability for few-shot classification algorithms. Our results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones. In a realistic cross-domain evaluation setting, we show that a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms.

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。

↑