Size-Adaptive Convolutional Neural Network with Parameterized-Swish Activation for Enhanced Object Detection

In computer vision, accurately detecting objects of varying sizes is essential for various applications, such as autonomous vehicle navigation and medical imaging diagnostics. Addressing the variance in object sizes presents a significant challenge requiring advanced computational solutions for reliable object recognition and processing. This research introduces a size-adaptive Convolutional Neural Network (CNN) framework to enhance detection performance across different object sizes. By dynamically adjusting the CNN’s configuration based on the observed distribution of object sizes, the framework employs statistical analysis and algorithmic decision-making to improve detection capabilities. Further innovation is presented through the Parameterized-Swish activation function. Distinguished by its dynamic parameters, this function is designed to better adapt to varying input patterns. It exceeds the performance of traditional activation functions by enabling faster model convergence and increasing detection accuracy, showcasing the effectiveness of adaptive activation functions in enhancing object detection systems. The implementation of this model has led to notable performance improvements: a 11.4% increase in mean Average Precision (mAP) and a 40.63% increase in frames per second (FPS) for small objects, demonstrating enhanced detection speed and accuracy. The model has achieved a 48.42% reduction in training time for medium-sized objects while still improving mAP, indicating significant efficiency gains without compromising precision. Large objects have seen a 16.9% reduction in training time and a 76.04% increase in inference speed, showcasing the model’s ability to expedite processing times substantially. Collectively, these advancements contribute to a more than 12% increase in detection efficiency and accuracy across various scenarios, highlighting the model’s robustness and adaptability in addressing the critical challenge of size variance in object detection.

Author dc:creator

• Venkata Krishnan, Yashwanth Raj

Advisor dc:contributor.advisor

• Mohamed, El-Sharkawy

• Neural Network Algorithm
• Deep Learning
• Computer Vision

Statement dc:rights

• CC0 1.0 Universal

Licence dc:rights.uri

• https://creativecommons.org/publicdomain/zero/1.0

Language dc:language.iso

en_US

Identifier URI

https://doi.org/10.7912/Y0JK-6F73

OAI identifier oai:identifier

oai:scholarworks.indianapolis.iu.edu:1805/41150