how to understand the parameter of cls_2 and cls_2xmul?

[Dengshunge]

In the paper, the parameter of cls_2 is indicating whether the image is destructed or not. It is confirmed to the code in "LoadModel.py". However, what is the meaning of the parameter of cls_2xmul in "LoadModel.py". the output channels is 2*num_class. And when using the cls_2xmul, the swap label is "label+numcls" in "dataset_DCL.py".

Hope to answer, thanks.

[Javacr]

我也没看懂这一系列操作．代码中对抗模块是将破坏图片设置了新的标签（200-399）用于分类．也就是说在对抗分支中原图加上破坏图一共有400类了．既然赋予了不同的标签用于对抗分类，那么对抗的机理怎么能起到作用呢？毕竟cls_2模式的目的是达到无法区分原始图片和破坏图片．而cls_2xmul模式下却是为了区分是否为破坏图片．这样的话，解释性又与论文相反．虽然cls_2和cls_2xmul好像都能达到一个很好的效果，但是解释性方面让我有点懵逼．