Uncertainty Reduction for Active Image Clustering via a Hybrid Global-Local Uncertainty Model

We propose a novel combined global/local model for active semi-supervised spectral clustering based on the principle of uncertainty reduction. We iteratively compute the derivative of the eigenvectors produced by spectral decomposition with respect to each item/image, and combine this with local label entropy provided by the current clustering results in order to estimate the uncertainty reduction potential of each item in the dataset. We then generate pairwise queries with respect to the best candidate item and retrieve the needed constraints from the user. We evaluate our method using three different image datasets—faces, leaves and dogs, and consistently demonstrate performance superior to the current state-of-the-art.