Hierarchical Probabilistic Embeddings for Multi-View Image Classification.

We address the task of image classification, when the available spectral bands can vary from image to image. We propose a model that learns to represent uncertainty over latent features in a way that is conditioned on the available bands. We expect that images with fewer bands will generally be more difficult to classify and hence have higher uncertainty. We compare two strategies for training such a model, one which uses explicit hierarchical constraints and one which relies on implicit constraints. We evaluate both using RGB and multispectral imagery from the EuroSat dataset and find that the hierarchical approach improves the compatibility of the resulting distributions without sacrificing accuracy.