search

msracver / FCIS

Fully Convolutional Instance-aware Semantic Segmentation
MIT License
1.56k stars 415 forks source link

confused about inside/outside scores #46

Open xinghedyc opened 7 years ago

xinghedyc commented 7 years ago

Hi, thank you for sharing such great work. I'm confused about inside/outside scores discribed in your paper: There are three cases: 1) high inside score and low outside score: detection+, segmentation+;
2) low inside score and high outside score: detection+, segmentation-; 3) both scores are low: detection-,segmentation-. The two scores answer the two questions jointly via softmax and max operations.
could you explain it a little bit? Thanks a lot.

tianhaijie commented 6 years ago

@xinghedyc Hello,I see another question you raised in this repo and you solved it! I have the same problem as you raised.Can you please give me your e-mail so i can ask for some details! Thanks!! (I'm so sorry that i'm also confused about this problem raised here!! T T)

liyi14 commented 6 years ago

Inside scores predict whether a pixel is in the object's mask. Outside scores predict whether a pixel is in the object's box while NOT in the object's mask.