Design of Kernels in Convolutional Neural Networks for Image Classification
Abstract
Despite the effectiveness of convolutional neural networks (CNNs) for image classification, our understanding of the effect of shape of convolution kernels on learned representations is limited. In this work, we explore and employ the relationship between shape of kernels which define receptive fields (RFs) in CNNs for learning of feature representations and image classification. For this purpose, we present a feature visualization method for visualization of pixel-wise classification score maps of learned features. Motivated by our experimental results, and observations reported in the literature for modeling of visual systems, we propose a novel design of shape of kernels for learning of representations in CNNs.
Cite
Text
Sun et al. "Design of Kernels in Convolutional Neural Networks for Image Classification." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46478-7_4Markdown
[Sun et al. "Design of Kernels in Convolutional Neural Networks for Image Classification." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/sun2016eccv-design/) doi:10.1007/978-3-319-46478-7_4BibTeX
@inproceedings{sun2016eccv-design,
title = {{Design of Kernels in Convolutional Neural Networks for Image Classification}},
author = {Sun, Zhun and Ozay, Mete and Okatani, Takayuki},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {51-66},
doi = {10.1007/978-3-319-46478-7_4},
url = {https://mlanthology.org/eccv/2016/sun2016eccv-design/}
}