The matrix U and V in implementation

[RongKaiWeskerMA]

Thanks for implementing the paper! I am confused with the matrix U and V. These two matrices in the paper seem to be two different matrices. But in the implementation, they are initilialized as the same matrix as: self.bilinear_proj = torch.nn.Sequential(torch.nn.Conv2d(512,8192,kernel_size=1,bias=False), torch.nn.BatchNorm2d(8192), torch.nn.ReLU(inplace=True))

proj_1 = self.bilinear_proj(conv1) proj_2 = self.bilinear_proj(conv2)

[HeimingX]

I am also curious about the implementation of this part. Look forward the feedback from author @luyao777

[luyao777]

Calling this function repeatedly creates different instances.