mlsanityData to 7 Oct 2026

Fractional Max-Pooling

arXiv 1412.6071 ↗First posted 18 Dec 2014cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

Convolutional networks almost always incorporate some form of spatial pooling, and very often it is alpha times alpha max-pooling with alpha=2. Max-pooling act on the hidden layers of the network, reducing their size by an integer multiplicative factor alpha. The amazing by-product of discarding 75% of your data is that you build into the network a degree of invariance with respect to translations and elastic distortions. However, if you simply alternate convolutional layers with max-pooling layers, performance is limited due to the rapid reduction in spatial size, and the disjoint nature of the pooling regions. We have formulated a fractional version of max-pooling where alpha is allowed to take non-integer values. Our version of max-pooling is stochastic as there are lots of different ways of constructing suitable pooling regions. We find that our form of fractional max-pooling reduces overfitting on a variety of datasets: for instance, we improve on the state-of-the art for CIFAR-100 without even using dropout.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 11; 2023: 4; 2024: 2; 2025: 2; 2026: 3.

35 papers.

Sort:

By area:

  1. 2021Resolution learning in deep convolutional networks using scale-space theorycited by 26
  2. 2022Learning strides in convolutional neural networkscited by 25
  3. 2022A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Taskscited by 12
  4. 2021LocalDrop: A Hybrid Regularization for Deep Neural Networkscited by 8
  5. 2022Survey: Exploiting Data Redundancy for Optimization of Deep Learningcited by 6
  6. 2023A General Framework for Robust G-Invariance in G-Equivariant Networkscited by 5
  7. 2021Meta-learning of Pooling Layers for Character Recognitioncited by 3
  8. 2021Strengthening the Training of Convolutional Neural Networks By Using Walsh Matrixcited by 3
  9. 2021A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustnesscited by 3
  10. 2022Comparison Analysis of Traditional Machine Learning and Deep Learning Techniques for Data and Image Classificationcited by 3
  11. 2022Will there be a construction? Predicting road constructions based on heterogeneous spatiotemporal datacited by 3
  12. 2021LogAvgExp Provides a Principled and Performant Global Pooling Operatorcited by 2
23 more
  1. 2022Fuzzy Poolingcited by 2
  2. 2023FedAVO: Improving Communication Efficiency in Federated Learning with African Vultures Optimizercited by 2
  3. 2026Rethinking Token Reduction for Large Vision-Language Modelscited by 2
  4. 2021Maximal function pooling with applicationscited by 1
  5. 2021DNN Quantization with Attentioncited by 1
  6. 2021Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsamplingcited by 1
  7. 2022An application of Pixel Interval Down-sampling (PID) for dense tiny microorganism counting on environmental microorganism imagescited by 1
  8. 2022Differentiable Self-Adaptive Learning Ratecited by 1
  9. 2021A Structurally Regularized Convolutional Neural Network for Image Classification using Wavelet-based SubBand Decompositioncited by 0
  10. 2021Deep Learning Based Analysis of Prostate Cancer from MP-MRIcited by 0
  11. 2021Ordinal Poolingcited by 0
  12. 2021Unsupervised MKL in Multi-layer Kernel Machinescited by 0
  13. 2022Dilated Continuous Random Field for Semantic Segmentationcited by 0
  14. 2022Fully Convolutional Fractional Scalingcited by 0
  15. 2022Deep Multi-Branch CNN Architecture for Early Alzheimer's Detection from Brain MRIscited by 0
  16. 2023Scale-Space Hypernetworks for Efficient Biomedical Imagingcited by 0
  17. 2023ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and Multispectral Data Fusioncited by 0
  18. 2024Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibrationcited by 0
  19. 2024Seam Carving as Feature Pooling in CNNcited by 0
  20. 20253DPyranet Features Fusion for Spatio-temporal Feature Learningcited by 0
  21. 2025Automatic Extraction of Road Networks by using Teacher-Student Adaptive Structural Deep Belief Network and Its Application to Landslide Disastercited by 0
  22. 2026One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learningcited by 0
  23. 2026Mitigating Shortcut Learning: Texture-Penalized Prototype Networkscited by 0