# Unsupervised Deep Graph Matching Based on Cycle Consistency

arXiv: https://arxiv.org/abs/2307.08930 · HTML: https://mlsanity.com/paper/2307.08930/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 18 Jul 2023.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [Differentiation of Blackbox Combinatorial Solvers](https://mlsanity.com/paper/1912.02175/) (2019)
- [Rethinking and Improving Relative Position Encoding for Vision Transformer](https://mlsanity.com/paper/2107.14222/) (2021)
- [SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels](https://mlsanity.com/paper/1711.08920/) (2017)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [SPair-71k: A Large-scale Benchmark for Semantic Correspondence](https://mlsanity.com/paper/1908.10543/) (2019)
- [Robust Point Cloud Registration Framework Based on Deep Graph Matching](https://mlsanity.com/paper/2103.04256/) (2021)
- [Learning Dense Correspondence via 3D-guided Cycle Consistency](https://mlsanity.com/paper/1604.05383/) (2016)
- [Deep Graph Matching Consensus](https://mlsanity.com/paper/2001.09621/) (2020)
- [Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching](https://mlsanity.com/paper/1911.11308/) (2019)
- [Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers](https://mlsanity.com/paper/2003.11657/) (2020)
- [Unsupervised Learning of Robust Spectral Shape Matching](https://mlsanity.com/paper/2304.14419/) (2023)
- [FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence](https://mlsanity.com/paper/1702.00926/) (2017)
- [Unsupervised Deep Multi-Shape Matching](https://mlsanity.com/paper/2207.09610/) (2022)
- [A Unified Framework for Implicit Sinkhorn Differentiation](https://mlsanity.com/paper/2205.06688/) (2022)
- [A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching](https://mlsanity.com/paper/1612.05476/) (2016)
- [Fusion Moves for Graph Matching](https://mlsanity.com/paper/2101.12085/) (2021)
- [A Comparative Study of Graph Matching Algorithms in Computer Vision](https://mlsanity.com/paper/2207.00291/) (2022)
- [GLMNet: Graph Learning-Matching Networks for Feature Matching](https://mlsanity.com/paper/1911.07681/) (2019)
- [Joint Graph Learning and Matching for Semantic Feature Correspondence](https://mlsanity.com/paper/2109.00240/) (2021)
- [Initialization and Coordinate Optimization for Multi-way Matching](https://mlsanity.com/paper/1611.00838/) (2016)
- [Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections](https://mlsanity.com/paper/2103.17229/) (2021)
- [Dual Mesh Convolutional Networks for Human Shape Correspondence](https://mlsanity.com/paper/2103.12459/) (2021)

## Built on by (most cited first, 2 of 2)

- [Synchronous Diffusion for Unsupervised Smooth Non-Rigid 3D Shape Matching](https://mlsanity.com/paper/2407.08244/) (2024)
- [Correlation Clustering of Organoid Images](https://mlsanity.com/paper/2403.13376/) (2024)

## Abstract (arXiv)

We contribute to the sparsely populated area of unsupervised deep graph matching with application to keypoint matching in images. Contrary to the standard 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.