VNet:a versatile network to train real-time semantic segmentation models on a single GPU

Dear editor, Modern semantic segmentation,which has important appli-cations such as medical image analysis,image editing,and video surveillance,has made remarkable progress using deep convolution neural network models.Recently,an efficient real-time semantic segmentation method has received con-siderable attention,as intelligent edge devices not only have faster inference speed requirements for semantic segmenta-tion models but also cannot rely on the cloud services of data centers.There are two feasible approaches to develop an ef-ficient semantic segmentation model.The first approach is by designing efficient models:designing and developing the models'architecture from scratch(e.g.,ENet[1]).The sec-ond approach,which is less common but increasingly popu-lar,is network compression:to develop light-weight models(e.g.,ICNet[2])with pruning methods[3]that are widely used in image classification tasks.However,both these ap-proaches are difficult to follow to develop light-weight and fast semantic segmentation models without compromising on the accuracy of the models.