Comparison of Methods Generalizing Max- and Average-Pooling

2021/03/02 by Florentin Bieder, Bieder, Florentin, Robin Sandkühler +3 · 2 citations
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Medical Image Segmentation Techniques

paper · pdf · doi:10.48550/arxiv.2103.01746

openalex publication_date 2021/03/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Gradient-based learning applied to document recognition
• Learning Multiple Layers of Features from Tiny Images

Cited by

• DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligence
• Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systems

Related

• Alpha-Integration Pooling for Convolutional Neural Networks
• The Theoretical Expressiveness of Maxpooling
• Sorted Pooling in Convolutional Networks for One-shot Learning
• Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
• Maximal function pooling with applications