Classification of objects using deformed images is a challenge that has been studied extensively in computer vision and pattern recognition in the last decades. While convolutional neural networks (CNNs) have achieved impressive progress in object classification and recognition in some benchmark datasets, recent works show that their performance is severely degraded for classification and recognition using deformed images. Our works focus on improvement of robustness of learned deep feature representations to deformations by constructing CNNs with new essences.

Design of Kernels in Convolutional Neural Networks for Image Classification
European Conference on Computer Vision (ECCV) 2016
Zhun Sun, Mete Ozay, Takayuki Okatani
[link, arxiv]