Abstract
We cast shape matching as metric learning with convolutional networks. We break the end-to-end process of image representation into two parts. Firstly, well established efficient methods are chosen to turn the images into edge maps. Secondly, the network is trained with edge maps of landmark images, which are automatically obtained by a structure-from-motion pipeline. The learned representation is evaluated on a range of different tasks, providing improvements on challenging cases of domain generalization, generic sketch-based image retrieval or its fine-grained counterpart. In contrast to other methods that learn a different model per task, object category, or domain, we use the same network throughout all our experiments, achieving state-of-the-art results in multiple benchmarks.
Abstract (translated)
我们使用卷积网络将形状匹配作为度量学习。我们将图像表示的端到端过程分为两部分。首先,选择成熟的有效方法将图像转换为边缘图。其次,利用地标图像的边缘图来训练网络,其通过运动结构管道自动获得。学习的表示在一系列不同的任务上进行评估,提供对领域泛化的挑战性案例,基于通用草图的图像检索或其细粒度对应物的改进。与每个任务,对象类别或域学习不同模型的其他方法相比,我们在所有实验中使用相同的网络,在多个基准测试中实现最先进的结果。
URL
https://arxiv.org/abs/1709.03409