Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space
This work addresses the need for large labeled datasets in medical imaging by enhancing semi-supervised learning, though it appears incremental as it builds on existing self-ensembling methods.
The authors tackled the problem of semi-supervised learning in medical imaging by proposing a model that uses disentangled latent space for self-ensembling, achieving improved performance over related SSL models in multi-label classification on chest X-ray images.
The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to encourage consensus among ensemble predictions of unknown labels, improving generalization of the model by making it more insensitive to the latent space. Currently, such an ensemble is obtained by randomization such as dropout regularization and random data augmentation. In this work, we hypothesize -- from the generalization perspective -- that self-ensembling can be improved by exploiting the stochasticity of a disentangled latent space. To this end, we present a stacked SSL model that utilizes unsupervised disentangled representation learning as the stochastic embedding for self-ensembling. We evaluate the presented model for multi-label classification using chest X-ray images, demonstrating its improved performance over related SSL models as well as the interpretability of its disentangled representations.