使用分支GAN（Branched-GANs）的加性类别区分图
Additive Class Distinction Maps using Branched-GANs
AI总结：
本研究提出基于分支GAN的加性类别区分图生成架构，通过图像分解将类别差异隔离在专用分支，实现像素级类别特征可视化，可应用于医学影像、航空影像分析等多模态任务。
摘要：
我们提出了一种新的模型、训练流程与架构，用于生成两类图像之间的精准区分图，目标是在像素级分辨率下理解一个类别的独有特征。这类图除了可实现可解释人工智能（XAI）的新功能外，还能助力自监督分割与目标检测。我们提出的架构基于图像分解，输出为多个生成网络（分支GAN，即branched-GANs）的输出之和，类别间的差异被隔离在一个专用分支中，该方法可对每个类别的独有特征实现清晰、精准且可解释的可视化。我们展示了这种通用方法如何应用于多种模态的各类任务，例如MRI脑肿瘤提取、航空摄影中的车辆隔离，以及获取女性与男性面部特征。本文是对我们初步发现与结果的初步报告。
英文摘要：
We present a new model, training procedure and architecture to create precise maps of distinction between two classes of images. The objective is to comprehend, in pixel-wise resolution, the unique characteristics of a class. These maps can facilitate self-supervised segmentation and objectdetection in addition to new capabilities in explainable AI (XAI). Our proposed architecture is based on image decomposition, where the output is the sum of multiple generative networks (branched-GANs). The distinction between classes is isolated in a dedicated branch. This approach allows clear, precise and interpretable visualization of the unique characteristics of each class. We show how our generic method can be used in several modalities for various tasks, such as MRI brain tumor extraction, isolating cars in aerial photography and obtaining feminine and masculine face features. This is a preliminary report of our initial findings and results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
