Semi-supervised Multiple Instance Learning using Variational Auto-Encoders

Ali Nihat Uzunalioglu, Tameem Adel, Jakub Mikolaj Tomczak

Keywords: Multiple-Instance Learning, Variational Autoencoders, Deep Generative Models

TL;DR: We extend the MIL classification problem to learning a joint distribution in the semi-supervised setting. We propose a latent variable model for the MIL generative model with a shared parameterization between the classifier and the unsupervised part

Abstract: We consider the multiple-instance learning (MIL) paradigm, which is a special case of supervised learning where training instances are grouped into bags. In MIL, the hidden instance labels do not have to be the same as the label of the comprising bag. On the other hand, the hybrid modelling approach is known to possess advantages basically due to the smooth consolidation of both discriminative and generative components. In this paper, we investigate whether we can get the best of both worlds (MIL and hybrid modelling), especially in a semi-supervised learning (SSL) setting. We first integrate a variational autoencoder (VAE), which is a powerful deep generative model, with an attention-based MIL classifier, then evaluate the performance of the resulting model in SSL. We assess the proposed approach on an established benchmark as well as a real-world medical dataset.