2019/07/22 by Prashnna Gyawali, Prashnna Kumar Gyawali, Zhiyuan Li +6
Computer Science · Mathematics · Medicine · #AI in cancer detection #COVID-19 diagnosis using AI #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1907.09607
arxiv created 2019/07/22 · openalex publication_date 2019/07/22 · arxiv updated 2019/07/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.