Comparison of Methods Generalizing Max- and Average-Pooling
This work addresses the problem of improving pooling methods for convolutional neural networks in image classification, but it is incremental as it shows no significant gains over existing approaches.
The paper compared various pooling methods that generalize max- and average-pooling, including a new smooth approximation method, using a VGG16 network on the Google Open Images v5 dataset, and found that none of the sophisticated methods performed significantly better than standard pooling in image classification.
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.