Multi-task Deep Learning Based CT Imaging Analysis For COVID-19: Classification and Segmentation

Amine Amyar; Romain Modzelewski; Su Ruan

Multi-task learning (MTL) [24] is a type of learning algorithm whose goal is to combine several pieces of information from different tasks to improve the performance of the model and its ability to better generalize [25] . The basic idea of MLT is that different tasks can share a common features representation [25] , and therefore, training them jointly. Using the whole dataset for the different tasks yield in a powerful representation and can improve performance for each task. Different approaches can be used in MTL such as hard parameter sharing [24] or soft parameter sharing [26] . Hard parameter sharing is the most commonly used approach to MTL in neural networks and greatly reduces the risk of overfitting [26] . It is generally applied by sharing the hidden layers between all . CC-BY-NC-ND 4.0 International license It is made available under a author/funder, who has granted medRxiv a license to display the preprint in perpetuity.