# Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration

arXiv: https://arxiv.org/abs/2408.02906 · HTML: https://mlsanity.com/paper/2408.02906/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 6 Aug 2024.

## Builds on (most cited first, 28 of 28)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Bayesian Deep Learning and a Probabilistic Perspective of Generalization](https://mlsanity.com/paper/2002.08791/) (2020)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [Ensemble Distribution Distillation](https://mlsanity.com/paper/1905.00076/) (2019)
- [Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation](https://mlsanity.com/paper/1904.07773/) (2019)
- [Subspace Inference for Bayesian Deep Learning](https://mlsanity.com/paper/1907.07504/) (2019)
- [Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentation](https://mlsanity.com/paper/1907.03338/) (2019)
- [Stochastic Pooling for Regularization of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1301.3557/) (2013)
- [AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling](https://mlsanity.com/paper/2111.00772/) (2021)
- [Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study](https://mlsanity.com/paper/2208.13365/) (2022)
- [Rethinking Confidence Calibration for Failure Prediction](https://mlsanity.com/paper/2303.02970/) (2023)
- [Fractional Max-Pooling](https://mlsanity.com/paper/1412.6071/) (2014)
- [Meta-Cal: Well-controlled Post-hoc Calibration by Ranking](https://mlsanity.com/paper/2105.04290/) (2021)
- [LIP: Local Importance-based Pooling](https://mlsanity.com/paper/1908.04156/) (2019)
- [Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning](https://mlsanity.com/paper/2212.10005/) (2022)
- [S3Pool: Pooling with Stochastic Spatial Sampling](https://mlsanity.com/paper/1611.05138/) (2016)
- [LiftPool: Bidirectional ConvNet Pooling](https://mlsanity.com/paper/2104.00996/) (2021)
- [Universal Pooling -- A New Pooling Method for Convolutional Neural Networks](https://mlsanity.com/paper/1907.11440/) (2019)
- [Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps](https://mlsanity.com/paper/2104.14124/) (2021)
- [Automatic Classification of Human Epithelial Type 2 Cell Indirect Immunofluorescence Images using Cell Pyramid Matching](https://mlsanity.com/paper/1403.3780/) (2014)

## Abstract (arXiv)

Spatial pooling (SP) and cross-channel pooling (CCP) operators have been applied to aggregate spatial features and pixel-wise features from feature maps in deep neural networks (DNNs), respectively. Their main goal is to reduce computation and memory overhead without visibly weakening the performance of DNNs. However, SP often faces the problem of losing the subtle feature representations, while CCP has a high possibility of ignoring salient feature representations, which may lead to both miscalibration of confidence issues and suboptimal medical classification results. To address these problems, we propose a novel dual-view framework, the first to systematically investigate the relative roles of SP and CCP by analyzing the difference between spatial features and pixel-wise features. Based on this framework, we propose a new pooling method, termed dual-view pyramid pooling (DVPP), to aggregate multi-scale dual-view features. DVPP aims to boost both medical image classification and confidence calibration performance by fully leveraging the merits of SP and CCP operators from a dual-axis perspective. Additionally, we discuss how to fulfill DVPP with five parameter-free implementations. Extensive experiments on six 2D/3D medical image classification tasks show that our DVPP surpasses state-of-the-art pooling methods in terms of medical image classification results and confidence calibration across different DNNs.