# Detail-Preserving Pooling in Deep Networks

arXiv: https://arxiv.org/abs/1804.04076 · HTML: https://mlsanity.com/paper/1804.04076/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2018.

## Built on by (most cited first, 26 of 26)

- [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)
- [Learning strides in convolutional neural networks](https://mlsanity.com/paper/2202.01653/) (2022)
- [Temporal Lift Pooling for Continuous Sign Language Recognition](https://mlsanity.com/paper/2207.08734/) (2022)
- [UniNet: Unified Architecture Search with Convolution, Transformer, and MLP](https://mlsanity.com/paper/2110.04035/) (2021)
- [LiftPool: Bidirectional ConvNet Pooling](https://mlsanity.com/paper/2104.00996/) (2021)
- [Self-Attentive Pooling for Efficient Deep Learning](https://mlsanity.com/paper/2209.07659/) (2022)
- [Learning Deep Morphological Networks with Neural Architecture Search](https://mlsanity.com/paper/2106.07714/) (2021)
- [Content-Adaptive Downsampling in Convolutional Neural Networks](https://mlsanity.com/paper/2305.09504/) (2023)
- [Meta-learning of Pooling Layers for Character Recognition](https://mlsanity.com/paper/2103.09528/) (2021)
- [Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks](https://mlsanity.com/paper/2109.06638/) (2021)
- [Dynamic U-Net: Adaptively Calibrate Features for Abdominal Multi-organ Segmentation](https://mlsanity.com/paper/2403.07303/) (2024)
- [LogAvgExp Provides a Principled and Performant Global Pooling Operator](https://mlsanity.com/paper/2111.01742/) (2021)
- [NOAH: Learning Pairwise Object Category Attentions for Image Classification](https://mlsanity.com/paper/2402.02377/) (2024)
- [A new approach to extracting coronary arteries and detecting stenosis in invasive coronary angiograms](https://mlsanity.com/paper/2101.09848/) (2021)
- [Logarithmic Morphological Neural Nets robust to lighting variations](https://mlsanity.com/paper/2204.09319/) (2022)
- [Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling](https://mlsanity.com/paper/2205.15571/) (2022)
- [Progressive Meta-Pooling Learning for Lightweight Image Classification Model](https://mlsanity.com/paper/2301.10038/) (2023)
- [Modeling the Nonsmoothness of Modern Neural Networks](https://mlsanity.com/paper/2103.14731/) (2021)
- [Fully Convolutional Fractional Scaling](https://mlsanity.com/paper/2203.10670/) (2022)
- [UniNet: Unified Architecture Search with Convolution, Transformer, and MLP](https://mlsanity.com/paper/2207.05420/) (2022)
- [Decomposing and Coupling Saliency Map for Lesion Segmentation in Ultrasound Images](https://mlsanity.com/paper/2308.00947/) (2023)
- [Redefining the Down-Sampling Scheme of U-Net for Precision Biomedical Image Segmentation](https://mlsanity.com/paper/2602.19412/) (2026)
- [FlexPooling with Simple Auxiliary Classifiers in Deep Networks](https://mlsanity.com/paper/2606.14926/) (2026)
- [UECP: Uncertainty-Enhanced Collaborative Perception](https://mlsanity.com/paper/2606.23046/) (2026)
- [MorphoSHAP: Rethinking the Unit of Attribution in Explanation for Deep Visual Models](https://mlsanity.com/paper/2609.25815/) (2026)

## Abstract (arXiv)

Most convolutional neural networks use some method for gradually downscaling the size of the hidden layers. This is commonly referred to as pooling, and is applied to reduce the number of parameters, improve invariance to certain distortions, and increase the receptive field size. Since pooling by nature is a lossy process, it is crucial that each such layer maintains the portion of the activations that is most important for the network's discriminability. Yet, simple maximization or averaging over blocks, max or average pooling, or plain downsampling in the form of strided convolutions are the standard. In this paper, we aim to leverage recent results on image downscaling for the purposes of deep learning. Inspired by the human visual system, which focuses on local spatial changes, we propose detail-preserving pooling (DPP), an adaptive pooling method that magnifies spatial changes and preserves important structural detail. Importantly, its parameters can be learned jointly with the rest of the network. We analyze some of its theoretical properties and show its empirical benefits on several datasets and networks, where DPP consistently outperforms previous pooling approaches.