DSS-pytorch icon indicating copy to clipboard operation
DSS-pytorch copied to clipboard

boundary noise

Open GuideWsp opened this issue 7 years ago • 1 comments

I train the DSS models, and test it. when i test it, i found that: the saliency object boundary have too much noise. do u have the same problem? maybe the reason is that: the code use mean to fuse, while the paper use a conv layer to fuse. i will try it later.

GuideWsp avatar Sep 17 '18 08:09 GuideWsp

  1. This is caused by “inference” (the z_fuse achieve here is a little different),the paper use z_fuse, z_2, z_3, z_4. You can see the output of demo (s-out6 and fusion without blur boundary)
  2. Current results is based on average fusion stragedy, I will train a learnable fusion soon(the paper using learnable way)

AceCoooool avatar Oct 12 '18 10:10 AceCoooool