2020/09/14 by Vahit Buğra Yeşilkaynak, Vahit Bugra Yesilkaynak, Yesilkaynak, Vahit Bugra +6 · 1 citation
Computer Science · Medicine · #Advanced Neural Network Applications #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #cs.CV
paper · pdf · doi:10.48550/arxiv.2009.06469
openalex publication_date 2020/09/14 · arxiv created 2020/10/09 · arxiv updated 2020/10/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep neural network training without pre-trained weights and few data is shown to need more training iterations. It is also known that, deeper models are more successful than their shallow counterparts for semantic segmentation task. Thus, we introduce EfficientSeg architecture, a modified and scalable version of U-Net, which can be efficiently trained despite its depth. We evaluated EfficientSeg architecture on Minicity dataset and outperformed U-Net baseline score (40% mIoU) using the same parameter count (51.5% mIoU). Our most successful model obtained 58.1% mIoU score and got the fourth place in semantic segmentation track of ECCV 2020 VIPriors challenge.