使用分支 GAN 生成叠加类别分割图（英文版）

英文标题：Additive Class Distinction Maps using Branched-GANs中文摘要：通过图像分解和多个生成网络的总和，本文提出了一种新模型、训练过程和体系结构以创建精确的图像类别区分地图，该方法允许对不同方法的应用，并通过可解释 AI 实现自我监督分割和物体检测。英文摘要：We present a new model, training procedure and architecture to create precisemaps of distinction between two classes of images. The objective is tocomprehend, in pixel-wise resolution, the unique characteristics of a class.These maps can facilitate self-supervised segmentation and objectdetection inaddition to new capabilities in explainable