A major area of growth within deep learning has been the study and implementation of convolutional neural networks. The general explanation within the deep learning community of the robustness of convolutional neural networks (CNNs) within image recognition rests upon the idea that CNNs are able to extract localized features. However, recent developments in fields such as Natural Language Processing are demonstrating that this paradigm may be incorrect. In this paper, we analyze the current state of the field concerning CNN's and present a hypothesis that provides a novel explanation for the robustness of CNN models. From there, we demonstrate the effectiveness of our approach by presenting novel deep CNN frame interpolation architecture that is comparable to the state of the art interpolation models with a fraction of the complexity.
@article{arxiv.1809.05286,
title = {Deep CNN Frame Interpolation with Lessons Learned from Natural Language Processing},
author = {Kian Ghodoussi and Nihar Sheth and Zane Durante and Markie Wagner},
journal= {arXiv preprint arXiv:1809.05286},
year = {2018}
}