Big Data Breakthroughs

Recently, study object detection, classification, segmentation, OCR, etc of computer vision, and review related papers. Reviewed the paper, "U-Net: Convolutional Networks for Biomedical Image Segmentation", which is a deep learning architecture for image segmentation tasks that consists of a contracting path and an expansive path connected by skip connections to retain fine details. Contracting Path: Convolution Bottleneck: Path from contracting to expansive Expansive Path: Concatenation with the correspondingly cropped feature map from the contracting path There are good articles and reviews about U-net, so I highlighted unpadding, elastic deformation, and normalization in image segmentation. Q1. In the trade-off between model accuracy and training efficiency, the paper suggested using unpadded convolutions and reducing the batch to a single image. Is it possible or okay to use padding in U Net and when we use it, is it efficient? A1. In the U Net architecture, instead of us...