The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) is the premier annual computer vision event. CVPR 2022 was held in a hybrid format which involved remote and in-person participation. The conference took place in New Orleans in the United States from 19/6 to 24/6.

Title

How does explicit orientation encoding affect image classification of ConvNets?

Authors

Ahmad Hammoudeh and Stéphabe Dupont

Abstract

Some shapes look different to us if rotated. That is attributed to the use of a rotation frame of coordinates in the human visual system. However, no evidence that ConvNets, which is a machine learning architecture, use a frame of coordinates for rotation. We investigated the effect of adding one to ConvNets. An explicit orientation encoding kernel was developed using a mathematically inspired self-supervised approach. The experimental results showed that rotation encoding improved the accuracy of classifying rotated images and the resilience against noise.