Interpretable Image Clustering via Diffeomorphism-Aware K-Means
This work addresses the problem of improving interpretability in image clustering for researchers and practitioners by making K-means robust to image deformations, offering a competitive but incremental improvement over existing methods.
This paper introduces an interpretable image clustering algorithm that applies K-means in the image space while accounting for nonlinear image deformations. It achieves this by developing a diffeomorphism-aware similarity measure, making the clustering invariant to such transformations, and leverages Thin-Plate Spline interpolation for efficiency. Numerical simulations indicate that the method performs competitively with state-of-the-art approaches across various datasets.
We design an interpretable clustering algorithm aware of the nonlinear structure of image manifolds. Our approach leverages the interpretability of $K$-means applied in the image space while addressing its clustering performance issues. Specifically, we develop a measure of similarity between images and centroids that encompasses a general class of deformations: diffeomorphisms, rendering the clustering invariant to them. Our work leverages the Thin-Plate Spline interpolation technique to efficiently learn diffeomorphisms best characterizing the image manifolds. Extensive numerical simulations show that our approach competes with state-of-the-art methods on various datasets.