Pre-rotation Only at Inference-Stage: A Way to Rotation Invariance of Convolutional Neural Networks

Pre-rotation Only at Inference-Stage: A Way to Rotation Invariance of Convolutional Neural Networks

Abstract The popular convolutional neural networks (CNN) require data augmentation to achieve rotation invariance. We propose an alternative mechanism, Pre-Rotation Only at Inference stage (PROAI), to make CNN rotation invariant. The overall idea is to learn how the human brain observe images. At th...

Full description

Bibliographic Details
Main Authors: Yue Fan, Peng Zhang, Jingqi Han, Dandan Liu, Jinsong Tang, Guoping Zhang
Format: Article
Language:English
Published: Springer 2024-04-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Rotated image recognition
Orientation estimation
Convolutional neural networks
Rotation invariance
Online Access:https://doi.org/10.1007/s44196-024-00490-z

Internet

https://doi.org/10.1007/s44196-024-00490-z

Similar Items