ClusterFuG: Clustering Fully connected Graphs by Multicut
This work addresses graph clustering challenges in computer vision, offering a more efficient and expressive method for tasks like instance segmentation and image clustering, though it appears incremental as it builds on existing multicut and correlation clustering frameworks.
The paper tackles the problem of clustering fully connected graphs by proposing a dense multicut formulation that eliminates the need for specifying graph topology and allows for weighted costs, resulting in algorithms that scale to tens of thousands of nodes and show empirical improvements on datasets like Cityscapes and ImageNet.
We propose a graph clustering formulation based on multicut (a.k.a. weighted correlation clustering) on the complete graph. Our formulation does not need specification of the graph topology as in the original sparse formulation of multicut, making our approach simpler and potentially better performing. In contrast to unweighted correlation clustering we allow for a more expressive weighted cost structure. In dense multicut, the clustering objective is given in a factorized form as inner products of node feature vectors. This allows for an efficient formulation and inference in contrast to multicut/weighted correlation clustering, which has at least quadratic representation and computation complexity when working on the complete graph. We show how to rewrite classical greedy algorithms for multicut in our dense setting and how to modify them for greater efficiency and solution quality. In particular, our algorithms scale to graphs with tens of thousands of nodes. Empirical evidence on instance segmentation on Cityscapes and clustering of ImageNet datasets shows the merits of our approach.