search

hq-jiang / instance-segmentation-with-discriminative-loss-tensorflow

Tensorflow implementation of "Semantic Instance Segmentation with a Discriminative Loss Function"
MIT License
170 stars 47 forks source link

paper issue #10

Closed pengyiwu closed 5 years ago

pengyiwu commented 5 years ago

hello ,i have read the paper"Towards End-to-End Lane Detection: an Instance Segmentation Approach" do you know what's the meaning of the "bounded inverse class weighting"(to solve the problem that the lane lines area is too small). i can not find the detailed explanation about the "bounded inverse class weighting" thanks so much!

hq-jiang commented 5 years ago

As I understand, you just weight the classes anti proportional to their frequency and have some cutoff value. I think, I did the same but hardcoded the values

pengyiwu commented 5 years ago

i just want to use the binary segmentation branch, how to change your code? the meanshift cluster is so slow. thanks a lot!