DMS: Differentiable Mean Shift for Dataset Agnostic Task Specific Clustering Using Side Information
This addresses the challenge of task-specific clustering for machine learning applications where traditional methods only find obvious clusters, though it may be incremental in combining mean shift with neural networks.
The paper tackles the problem of clustering data using side information in the form of pairwise examples, without needing prior knowledge of cluster numbers, centers, or distance metrics, and achieves state-of-the-art performance in both intrinsic and non-intrinsic dataset tasks.
We present a novel approach, in which we learn to cluster data directly from side information, in the form of a small set of pairwise examples. Unlike previous methods, with or without side information, we do not need to know the number of clusters, their centers or any kind of distance metric for similarity. Our method is able to divide the same data points in various ways dependant on the needs of a specific task, defined by the side information. Contrastingly, other work generally finds only the intrinsic, most obvious, clusters. Inspired by the mean shift algorithm, we implement our new clustering approach using a custom iterative neural network to create Differentiable Mean Shift (DMS), a state of the art, dataset agnostic, clustering method. We found that it was possible to train a strong cluster definition without enforcing a constraint that each cluster must be presented during training. DMS outperforms current methods in both the intrinsic and non-intrinsic dataset tasks.