Unsupervised Deep Graph Matching Based on Cycle Consistency

TL;DR

This paper introduces an unsupervised deep graph matching method for keypoint matching in images, leveraging cycle consistency and black-box differentiation to avoid ground truth labels and achieve state-of-the-art results.

Contribution

It presents a novel unsupervised learning approach for deep graph matching that does not require labeled correspondences, using cycle consistency and differentiable combinatorial solvers.

Findings

Sets new state-of-the-art in unsupervised graph matching.

Flexible framework compatible with various architectures.

Effective in keypoint matching without supervision.

Abstract

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.