Comparison of Methods Generalizing Max- and Average-Pooling
Computer Vision and Pattern Recognition
2021-03-03 v1 Machine Learning
Abstract
Max- and average-pooling are the most popular pooling methods for downsampling in convolutional neural networks. In this paper, we compare different pooling methods that generalize both max- and average-pooling. Furthermore, we propose another method based on a smooth approximation of the maximum function and put it into context with related methods. For the comparison, we use a VGG16 image classification network and train it on a large dataset of natural high-resolution images (Google Open Images v5). The results show that none of the more sophisticated methods perform significantly better in this classification task than standard max- or average-pooling.
Cite
@article{arxiv.2103.01746,
title = {Comparison of Methods Generalizing Max- and Average-Pooling},
author = {Florentin Bieder and Robin Sandkühler and Philippe C. Cattin},
journal= {arXiv preprint arXiv:2103.01746},
year = {2021}
}
Comments
16 pages, 6 figures