In this paper, we show that this task can be addressed effectively by leveraging instead 2D pre-trained models for instance segmentation.

The performance of spectral clustering heavily relies on the quality of affinity matrix.

Recent advances in center-based clustering continue to improve upon the drawbacksofLloyd'scelebrated k-meansalgorithmover 60yearsafteritsintroduction.

More generally, any finite subset of a hyperbolic space "looks like" a finite tree.

Our paper adopts the CP decomposition because it handles heterogeneity in each mode, learns the clustering patterns across different modes of data in amore independent way, and provides flexibility for clustering a certain mode of the tensor without being affected by correlation with other modes. Our method is similar to those in a recent series of papers [27, 21] that use the CP decomposition structure. Note that their estimation algorithms use the framework oftensor power method [1].