NIRMAL Pooling: An Adaptive Max Pooling Approach with Non-linear Activation for Enhanced Image Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gaud, Nirmal, Jha, Krishna Kumar, Adhikari, Jhimli, S, Adhini Nasarin P, Das, Joydeep, Deshpande, Samarth S, Barara, Nitasha, Ramya, Vaduguru Venkata, Saha, Santu, Baran, Mehmet Tarik, Venkateshwarlu, Sarangi, D, Anusha M, Mouli, Surej, Katiyar, Preeti, Chaudhary, Vipin Kumar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912538184122368
author Gaud, Nirmal
Jha, Krishna Kumar
Adhikari, Jhimli
S, Adhini Nasarin P
Das, Joydeep
Deshpande, Samarth S
Barara, Nitasha
Ramya, Vaduguru Venkata
Saha, Santu
Baran, Mehmet Tarik
Venkateshwarlu, Sarangi
D, Anusha M
Mouli, Surej
Katiyar, Preeti
Chaudhary, Vipin Kumar
author_facet Gaud, Nirmal
Jha, Krishna Kumar
Adhikari, Jhimli
S, Adhini Nasarin P
Das, Joydeep
Deshpande, Samarth S
Barara, Nitasha
Ramya, Vaduguru Venkata
Saha, Santu
Baran, Mehmet Tarik
Venkateshwarlu, Sarangi
D, Anusha M
Mouli, Surej
Katiyar, Preeti
Chaudhary, Vipin Kumar
contents This paper presents NIRMAL Pooling, a novel pooling layer for Convolutional Neural Networks (CNNs) that integrates adaptive max pooling with non-linear activation function for image classification tasks. The acronym NIRMAL stands for Non-linear Activation, Intermediate Aggregation, Reduction, Maximum, Adaptive, and Localized. By dynamically adjusting pooling parameters based on desired output dimensions and applying a Rectified Linear Unit (ReLU) activation post-pooling, NIRMAL Pooling improves robustness and feature expressiveness. We evaluated its performance against standard Max Pooling on three benchmark datasets: MNIST Digits, MNIST Fashion, and CIFAR-10. NIRMAL Pooling achieves test accuracies of 99.25% (vs. 99.12% for Max Pooling) on MNIST Digits, 91.59% (vs. 91.44%) on MNIST Fashion, and 70.49% (vs. 68.87%) on CIFAR-10, demonstrating consistent improvements, particularly on complex datasets. This work highlights the potential of NIRMAL Pooling to enhance CNN performance in diverse image recognition tasks, offering a flexible and reliable alternative to traditional pooling methods.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10940
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NIRMAL Pooling: An Adaptive Max Pooling Approach with Non-linear Activation for Enhanced Image Classification
Gaud, Nirmal
Jha, Krishna Kumar
Adhikari, Jhimli
S, Adhini Nasarin P
Das, Joydeep
Deshpande, Samarth S
Barara, Nitasha
Ramya, Vaduguru Venkata
Saha, Santu
Baran, Mehmet Tarik
Venkateshwarlu, Sarangi
D, Anusha M
Mouli, Surej
Katiyar, Preeti
Chaudhary, Vipin Kumar
Computer Vision and Pattern Recognition
This paper presents NIRMAL Pooling, a novel pooling layer for Convolutional Neural Networks (CNNs) that integrates adaptive max pooling with non-linear activation function for image classification tasks. The acronym NIRMAL stands for Non-linear Activation, Intermediate Aggregation, Reduction, Maximum, Adaptive, and Localized. By dynamically adjusting pooling parameters based on desired output dimensions and applying a Rectified Linear Unit (ReLU) activation post-pooling, NIRMAL Pooling improves robustness and feature expressiveness. We evaluated its performance against standard Max Pooling on three benchmark datasets: MNIST Digits, MNIST Fashion, and CIFAR-10. NIRMAL Pooling achieves test accuracies of 99.25% (vs. 99.12% for Max Pooling) on MNIST Digits, 91.59% (vs. 91.44%) on MNIST Fashion, and 70.49% (vs. 68.87%) on CIFAR-10, demonstrating consistent improvements, particularly on complex datasets. This work highlights the potential of NIRMAL Pooling to enhance CNN performance in diverse image recognition tasks, offering a flexible and reliable alternative to traditional pooling methods.
title NIRMAL Pooling: An Adaptive Max Pooling Approach with Non-linear Activation for Enhanced Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.10940