Deep Shape Matching
It provides a unified approach for shape matching that improves performance in various tasks without needing task-specific models.
The paper tackles shape matching by using metric learning with convolutional networks on edge maps, achieving state-of-the-art results across multiple benchmarks including domain generalization and sketch-based image retrieval.
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.