GASP, a Generalized Framework for Agglomerative Clustering of Signed Graphs and Its Application to Instance Segmentation

Alberto Bailoni, Constantin Pape, Nathan Hütsch, Steffen Wolf, Thorsten Beier, Anna Kreshuk, Fred A. Hamprecht; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 11645-11655

Abstract


We propose a theoretical framework that generalizes simple and fast algorithms for hierarchical agglomerative clustering to weighted graphs with both attractive and repulsive interactions between the nodes. This framework defines GASP, a Generalized Algorithm for Signed graph Partitioning, and allows us to explore many combinations of different linkage criteria and cannot-link constraints. We prove the equivalence of existing clustering methods to some of those combinations and introduce new algorithms for combinations that have not been studied before. We study both theoretical and empirical properties of these combinations and prove that some of these define an ultrametric on the graph. We conduct a systematic comparison of various instantiations of GASP on a large variety of both synthetic and existing signed clustering problems, in terms of accuracy but also efficiency and robustness to noise. Lastly, we show that some of the algorithms included in our framework, when combined with the predictions from a CNN model, result in a simple bottom-up instance segmentation pipeline. Going all the way from pixels to final segments with a simple procedure, we achieve state-of-the-art accuracy on the CREMI 2016 EM segmentation benchmark without requiring domain-specific superpixels.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Bailoni_2022_CVPR, author = {Bailoni, Alberto and Pape, Constantin and H\"utsch, Nathan and Wolf, Steffen and Beier, Thorsten and Kreshuk, Anna and Hamprecht, Fred A.}, title = {GASP, a Generalized Framework for Agglomerative Clustering of Signed Graphs and Its Application to Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {11645-11655} }