Transferable Deep Metric Learning for Clustering
This addresses the challenge of metric selection for clustering across diverse domains, though it is incremental as it builds on existing deep metric learning approaches.
The paper tackles the problem of clustering in high-dimensional spaces by learning a transferable metric that can be applied across different datasets, achieving competitive results with state-of-the-art methods on synthetic, MNIST, SVHN, and omniglot datasets using only a small number of labelled training datasets and shallow networks.
Clustering in high dimension spaces is a difficult task; the usual distance metrics may no longer be appropriate under the curse of dimensionality. Indeed, the choice of the metric is crucial, and it is highly dependent on the dataset characteristics. However a single metric could be used to correctly perform clustering on multiple datasets of different domains. We propose to do so, providing a framework for learning a transferable metric. We show that we can learn a metric on a labelled dataset, then apply it to cluster a different dataset, using an embedding space that characterises a desired clustering in the generic sense. We learn and test such metrics on several datasets of variable complexity (synthetic, MNIST, SVHN, omniglot) and achieve results competitive with the state-of-the-art while using only a small number of labelled training datasets and shallow networks.