mlsanityData to 7 Oct 2026

Comparison of Methods Generalizing Max- and Average-Pooling

arXiv 2103.01746 ↗First posted 2 Mar 2021cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 11 of its 23 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

11 of 23 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  8. 2015Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Treecited by 36
  9. 2013Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networkscited by 32
  10. 2017Quantifying Translation-Invariance in Convolutional Neural Networkscited by 30
  11. 2018Adaptive pooling operators for weakly labeled sound event detectioncited by 21

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 4.

6 papers.

  1. 2025CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selectioncited by 8
  2. 2025Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Studycited by 6
  3. 2023A General Framework for Robust G-Invariance in G-Equivariant Networkscited by 5
  4. 2023Using Neural Networks for Fast SAR Roughness Estimation of High Resolution Imagescited by 1
  5. 2025Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systemscited by 0
  6. 2025DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligencecited by 0