Gabor Filters as Initializers for Convolutional Neural Networks: A Study on Inductive Bias and Performance on Image Classification
Abstract
This study explores the impact of Gabor filters on Convolutional Neural Networks (CNNs) performance in image classification tasks. Prior research has indicated that the receptive filters of CNNs often resemble Gabor filters, suggesting their potential as initial receptive filters. We conducted an extensive analysis on various general object datasets, demonstrating that integrating Gabor filters in the receptive layer enhances CNN performance, as evidenced by improved accuracy, higher Area Under the Curve (AUC), and reduced loss. Furthermore, our findings suggest that CNNs equipped with Gabor filters in the receptive layer can perform better in a shorter training period than traditional random initialization techniques.
Cite
Text
Rivas and Rai. "Gabor Filters as Initializers for Convolutional Neural Networks: A Study on Inductive Bias and Performance on Image Classification." ICML 2023 Workshops: LXAI_Regular_Deadline, 2023.Markdown
[Rivas and Rai. "Gabor Filters as Initializers for Convolutional Neural Networks: A Study on Inductive Bias and Performance on Image Classification." ICML 2023 Workshops: LXAI_Regular_Deadline, 2023.](https://mlanthology.org/icmlw/2023/rivas2023icmlw-gabor/)BibTeX
@inproceedings{rivas2023icmlw-gabor,
title = {{Gabor Filters as Initializers for Convolutional Neural Networks: A Study on Inductive Bias and Performance on Image Classification}},
author = {Rivas, Pablo and Rai, Mehang},
booktitle = {ICML 2023 Workshops: LXAI_Regular_Deadline},
year = {2023},
url = {https://mlanthology.org/icmlw/2023/rivas2023icmlw-gabor/}
}