From Label Maps to Generative Shape Models: A Variational Bayesian Learning Approach

Shireen Y. Elhabian, Ross T. Whitaker

Abstract: This paper proposes a Bayesian treatment of a latent variable model for learning generative shape models of grid-structured representations, aka label maps, that relies on direct probabilistic formulation with a variational approach for deterministic model learning. Spatial coherency and sparsity priors are incorporated to lend stability to the optimization problem, thereby regularizing the solution space while avoiding overfitting in this high-dimensional, low-sample-size scenario. Hyperparameters are estimated in closed-form using type-II maximum likelihood to avoid grid searches. Further, a mixture formulation is proposed to capture nonlinear shape variations in a way that balances the model expressiveness with the efficiency of learning and inference. Experiments show that the proposed model outperforms state-of-the-art representations on real datasets w.r.t. generalization to unseen samples.