NIRMAL Pooling: An Adaptive Max Pooling Approach with Non-linear Activation for Enhanced Image Classification
Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
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
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7075994193
Cites:
Cited by:
Related to: