当前位置: X-MOL 学术Sci. China Inf. Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Learning to focus: cascaded feature matching network for few-shot image recognition
Science China Information Sciences ( IF 8.8 ) Pub Date : 2021-07-30 , DOI: 10.1007/s11432-020-2973-7
Mengting Chen 1 , Xinggang Wang 1 , Wenyu Liu 1 , Heng Luo 2 , Yifeng Geng 2
Affiliation  

Generally, deep networks learn to recognize a category of objects by training on a large number of annotated images accurately. However, a meta-learning problem known as a low-shot image recognition task occurs when a few images with annotations are available for learning a recognition model for a single category. Consequently, the objects in testing/query and training/support image datasets are likely to vary in terms of size, location, style, and so on. In this paper, we propose a method, cascaded feature matching network (CFMN), to solve this problem. We train the meta-learner to learn a more fine-grained and adaptive deep distance metric using feature matching block, which aligns associated features together and naturally ignores non-discriminative features. By applying the proposed feature matching block in different layers of the network, multi-scale information among the compared images is incorporated into the final cascaded matching feature, which boosts the recognition performance and generalizes better by learning on relationships. Moreover, the experiments for few-shot learning (FSL) using two standard datasets: miniImageNet and Omniglot, confirm the effectiveness of our proposed method. Besides, the multi-label few-shot task is first studied on a new data split of the COCO dataset, which further shows the superiority of the proposed feature matching network when performing the FSL in complex images.



中文翻译:

学习聚焦:用于少镜头图像识别的级联特征匹配网络

通常,深度网络通过对大量带注释的图像进行准确训练来学习识别一类对象。然而,当一些带有注释的图像可用于学习单个类别的识别模型时,就会出现称为低镜头图像识别任务的元学习问题。因此,测试/查询和训练/支持图像数据集中的对象可能在大小、位置、样式等方面有所不同。在本文中,我们提出了一种方法,级联特征匹配网络(CFMN)来解决这个问题。我们训练元学习器使用特征匹配块来学习更细粒度和自适应的深度距离度量,该块将相关特征对齐并自然地忽略非判别特征。通过在网络的不同层应用所提出的特征匹配块,比较图像之间的多尺度信息被合并到最终的级联匹配特征中,通过学习关系来提高识别性能并更好地泛化。此外,使用两个标准数据集 miniImageNet 和 Omniglot 的小样本学习 (FSL) 实验证实了我们提出的方法的有效性。此外,首先在 COCO 数据集的新数据拆分上研究了多标签少拍任务,这进一步表明了所提出的特征匹配网络在复杂图像中执行 FSL 时的优越性。miniImageNet 和 Omniglot,证实了我们提出的方法的有效性。此外,首先在 COCO 数据集的新数据拆分上研究了多标签少拍任务,这进一步表明了所提出的特征匹配网络在复杂图像中执行 FSL 时的优越性。miniImageNet 和 Omniglot,证实了我们提出的方法的有效性。此外,首先在 COCO 数据集的新数据拆分上研究了多标签少拍任务,这进一步表明了所提出的特征匹配网络在复杂图像中执行 FSL 时的优越性。

更新日期:2021-08-03
down
wechat
bug