Initialization of V-fusenet

[suntianren]

Hi, I'm very interested in your work. I have read your paper. It's very helpful. And i wish to know more about your experiments details.
Are the weights of the encoder in V-fusenet initialized with those of VGG-16 trained on ImageNet, or SegNet encoder trained on IRRG images and Composite images?

[Nicolas Audebert]

If I recall correctly, in the paper we initialized it using pretrained SegNets on IRRG and composite but you can train it end-to-end starting from VGG-16, it's just longer to converge.

[suntianren]

Thanks a lot :)