Handling Invalid Pixels in Convolutional Neural Networks
Most neural networks use a normal convolutional layer that assumes that all input pixels are valid pixels. However, pixels added to the input through padding result in adding extra information that was not initially present. This extra information can be considered invalid. Invalid pixels can also b...
Main Author: | |
---|---|
Other Authors: | |
Format: | Others |
Published: |
Virginia Tech
2020
|
Subjects: | |
Online Access: | http://hdl.handle.net/10919/98619 |