论文标题
几次学习的不对称分配度量
Asymmetric Distribution Measure for Few-shot Learning
论文作者
论文摘要
基于公制的几个图像分类的核心思想是直接测量查询图像和支持类之间的关系，以学习可转移的特征嵌入。先前的工作主要集中在图像级特征表示上，实际上由于样本的稀缺性，实际上无法有效地估算一类分布。最近的一些工作表明，基于本地描述符的表示形式可以比基于图像级的表示形式获得更丰富的表示形式。但是，此类工作仍然基于一个较不效率的实例级度量，尤其是对称度量标准，以衡量查询图像和支持类之间的关系。鉴于查询图像与支持类别之间的自然不对称关系，我们认为不对称度量更适合基于公制的少量学习。为此，我们提出了一种新型的不对称分布度量（ADM）网络，以通过计算两个多变量的查询和类别的多元局部分布之间的联合局部和全局不对称测量来进行几次学习。此外，提出了一种任务感知的对比度措施策略（CMS），以进一步增强措施函数。在流行的Miniimagenet和Tieredimagenet上，我们在$ 5 $ -Way $ 1 $ -1 $ -SHOT的任务上获得了$ 3.02 \％$和$ 1.56 \％$ $的收益，从而验证了我们对几次射击学习的不对称分配指标的创新设计。
The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class's distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relations between query images and support classes. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of queries and classes. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, we achieve $3.02\%$ and $1.56\%$ gains over the state-of-the-art method on the $5$-way $1$-shot task, respectively, validating our innovative design of asymmetric distribution measures for few-shot learning.
