Timezone: »

 
Poster
Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning
Runzhong Wang · Junchi Yan · Xiaokang Yang

Thu Dec 10 09:00 PM -- 11:00 PM (PST) @ Poster Session 6 #1848
in Poster Session 7 »

This paper considers the setting of jointly matching and clustering multiple graphs belonging to different groups, which naturally rises in many realistic problems. Both graph matching and clustering are challenging (NP-hard) and a joint solution is appealing due to the natural connection of the two tasks. In this paper, we resort to a graduated assignment procedure for soft matching and clustering over iterations, whereby the two-way constraint and clustering confidence are modulated by two separate annealing parameters, respectively. Our technique can be further utilized for end-to-end learning whose loss refers to the cross-entropy between two lines of matching pipelines, as such the keypoint feature extraction CNNs can be learned without ground-truth supervision. Experimental results on real-world benchmarks show our method outperforms learning-free algorithms and performs comparatively against two-graph based supervised graph matching approaches. Source code is publicly available as a module of ThinkMatch (https://github.com/Thinklab-SJTU/ThinkCO/tree/main/ThinkMatch).

Author Information

Runzhong Wang (Shanghai Jiao Tong University)
Junchi Yan (Shanghai Jiao Tong University)
Xiaokang Yang (Shanghai Jiao Tong University)

More from the Same Authors