tu-darmstadt-informatik/bsc-thesis
1
0
Fork 0
mirror of https://github.com/tu-darmstadt-informatik/bsc-thesis.git synced 2026-02-06 10:05:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update background.tex

Browse Source
This commit is contained in:
Simon Meister 2017-11-15 18:09:03 +01:00 committed by GitHub
parent 5712ba3341
commit 65a11d3a94
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
background.tex
View File

@ -345,7 +345,7 @@ might have lost too much spatial information to properly predict the exact bound
box and a high resolution mask. Likewise, for very big objects, the fixed size
RoI window might be too small to cover the region of the feature map containing
information for this object.
As a solution to this, the Feature Pyramid Network (FPN) \cite{FPN} enable features
As a solution to this, the Feature Pyramid Network (FPN) \cite{FPN} enables features
of an appropriate scale to be used, depending of the size of the bounding box.
For this, a pyramid of feature maps is created on top of the ResNet \cite{ResNet}
encoder by combining bilinear upsampled feature maps coming from the bottleneck