# S3Pool: Pooling with Stochastic Spatial Sampling

arXiv: https://arxiv.org/abs/1611.05138 · HTML: https://mlsanity.com/paper/1611.05138/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2016.

## Built on by (most cited first, 17 of 17)

- [AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling](https://mlsanity.com/paper/2111.00772/) (2021)
- [Refining activation downsampling with SoftPool](https://mlsanity.com/paper/2101.00440/) (2021)
- [Resolution learning in deep convolutional networks using scale-space theory](https://mlsanity.com/paper/2106.03412/) (2021)
- [Temporal Lift Pooling for Continuous Sign Language Recognition](https://mlsanity.com/paper/2207.08734/) (2022)
- [LiftPool: Bidirectional ConvNet Pooling](https://mlsanity.com/paper/2104.00996/) (2021)
- [A General Framework for Robust G-Invariance in G-Equivariant Networks](https://mlsanity.com/paper/2310.18564/) (2023)
- [Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks](https://mlsanity.com/paper/2109.06638/) (2021)
- [NOAH: Learning Pairwise Object Category Attentions for Image Classification](https://mlsanity.com/paper/2402.02377/) (2024)
- [CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving](https://mlsanity.com/paper/2505.16524/) (2025)
- [Local and Global Context-and-Object-part-Aware Superpixel-based Data Augmentation for Deep Visual Recognition](https://mlsanity.com/paper/2512.00130/) (2025)
- [Ordinal Pooling](https://mlsanity.com/paper/2109.01561/) (2021)
- [Fully Convolutional Fractional Scaling](https://mlsanity.com/paper/2203.10670/) (2022)
- [ME-CapsNet: A Multi-Enhanced Capsule Networks with Routing Mechanism](https://mlsanity.com/paper/2203.15547/) (2022)
- [A Novel Dual-pooling Attention Module for UAV Vehicle Re-identification](https://mlsanity.com/paper/2306.14104/) (2023)
- [Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration](https://mlsanity.com/paper/2408.02906/) (2024)
- [Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Pooling](https://mlsanity.com/paper/2505.18446/) (2025)
- [Redefining the Down-Sampling Scheme of U-Net for Precision Biomedical Image Segmentation](https://mlsanity.com/paper/2602.19412/) (2026)

## Abstract (arXiv)

Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding computational savings in subsequent convolutional layers. We view the pooling operation in CNNs as a two-step procedure: first, a pooling window (e.g., 2× 2) slides over the feature map with stride one which leaves the spatial resolution intact, and second, downsampling is performed by selecting one pixel from each non-overlapping pooling window in an often uniform and deterministic (e.g., top-left) manner. Our starting point in this work is the observation that this regularly spaced downsampling arising from non-overlapping windows, although intuitive from a signal processing perspective (which has the goal of signal reconstruction), is not necessarily optimal for learning (where the goal is to generalize). We study this aspect and propose a novel pooling strategy with stochastic spatial sampling (S3Pool), where the regular downsampling is replaced by a more general stochastic version. We observe that this general stochasticity acts as a strong regularizer, and can also be seen as doing implicit data augmentation by introducing distortions in the feature maps. We further introduce a mechanism to control the amount of distortion to suit different datasets and architectures. To demonstrate the effectiveness of the proposed approach, we perform extensive experiments on several popular image classification benchmarks, observing excellent improvements over baseline models. Experimental code is available at https://github.com/Shuangfei/s3pool.