We contribute to the sparsely populated area of unsupervised deep graph matching with application to keypoint matching in images. Contrary to the standard \emph{supervised} approach, our method does not require ground truth correspondences between keypoint pairs. Instead, it is self-supervised by enforcing consistency of matchings between images of the same object category. As the matching and the consistency loss are discrete, their derivatives cannot be straightforwardly used for learning. We address this issue in a principled way by building our method upon the recent results on black-box differentiation of combinatorial solvers. This makes our method exceptionally flexible, as it is compatible with arbitrary network architectures and combinatorial solvers. Our experimental evaluation suggests that our technique sets a new state-of-the-art for unsupervised graph matching.

本文研究了无监督深度图匹配，并应用于图像特征点匹配。与传统的有监督方法不同，我们的方法不需要关键点对之间的真实对应关系，而是通过强制同一物体类别图像之间的匹配一致性进行自我监督。由于匹配和一致性损失是离散的，不能直接用于学习，我们通过在组合求解器的黑盒微分结果的基础上构建方法来解决这个问题。这使得我们的方法非常灵活，可以与任意网络架构和组合求解器兼容。实验结果表明，我们的技术在无监督图匹配领域达到了最新的最先进水平。

基于循环一致性的无监督深度图匹配