Column drop: making CNNs invariant to image cropping
We introduce a new regularization technique column drop which uses inner structure of CNNs for classification to make its output invariant to random crops of input image. Use of this regularization eliminates need in data augmentation by random image cropping under some conditions on architecture of...
Saved in:
| Published in: | Штучний інтелект |
|---|---|
| Date: | 2018 |
| Main Authors: | , |
| Format: | Article |
| Language: | English |
| Published: |
Інститут проблем штучного інтелекту МОН України та НАН України
2018
|
| Subjects: | |
| Online Access: | https://nasplib.isofts.kiev.ua/handle/123456789/162372 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Journal Title: | Digital Library of Periodicals of National Academy of Sciences of Ukraine |
| Cite this: | Column drop: making CNNs invariant to image cropping / V.V. Dudar, V.V. Semenov // Штучний інтелект. — 2018. — № 2 (80). — С. 43-49. — Бібліогр.: 8 назв. — англ. |