search

nv-tlabs / GSCNN

Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
https://nv-tlabs.github.io/GSCNN/
Other
916 stars 200 forks source link

few questions with interesting result, outstanding architecture of yours #4

Closed wooramkang closed 5 years ago

wooramkang commented 5 years ago

  1. interesting result, outstanding architecture! when can i read your codes

  2. did your team consider more loss technics, something like VGG loss or something?

  3. this architecture could be called as one of transformation of encoder-decoder, right?

not question but additionally, there is typo on regular stream part of page 3 in in paper. fully-convoutional => fully-convolutional

thank you for reading it

tovacinni commented 5 years ago

Thanks for your interest in our work!

  1. We have released the code!

  2. We have considered several different loss functions, but have not tried VGG loss specifically.

  3. I think so!

Thanks for pointing out the typo, we will make amendments accordingly. :)

akshaykulkarni07 commented 4 years ago

How is it a transformation of encoder-decoder? I think it is based on the fully convolutional with upsampling approach. The encoder-decoder architectures use transposed convolutions (deconvolutions) for upsampling, whereas this work uses bilinear interpolations for all upsampling.