Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.04344 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909890217246720 |
|---|---|
| author | Shaikh, Muhammad Annas Zaman, Hamza Asif, Arbaz |
| author_facet | Shaikh, Muhammad Annas Zaman, Hamza Asif, Arbaz |
| contents | This paper presents a comprehensive evaluation of nine convolutional neural network architectures for binary classification of horses and motorcycles in the VOC 2008 dataset. We address the significant class imbalance problem by implementing minority-class augmentation techniques. Our experiments compare modern architectures including ResNet-50, ConvNeXt-Tiny, DenseNet-121, and Vision Transformer across multiple performance metrics. Results demonstrate substantial performance variations, with ConvNeXt-Tiny achieving the highest Average Precision (AP) of 95.53% for horse detection and 89.12% for motorcycle detection. We observe that data augmentation significantly improves minority class detection, particularly benefiting deeper architectures. This study provides insights into architecture selection for imbalanced binary classification tasks and quantifies the impact of data augmentation strategies in mitigating class imbalance issues in object detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04344 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparative Study of CNN Architectures for Binary Classification of Horses and Motorcycles in the VOC 2008 Dataset Shaikh, Muhammad Annas Zaman, Hamza Asif, Arbaz Computer Vision and Pattern Recognition This paper presents a comprehensive evaluation of nine convolutional neural network architectures for binary classification of horses and motorcycles in the VOC 2008 dataset. We address the significant class imbalance problem by implementing minority-class augmentation techniques. Our experiments compare modern architectures including ResNet-50, ConvNeXt-Tiny, DenseNet-121, and Vision Transformer across multiple performance metrics. Results demonstrate substantial performance variations, with ConvNeXt-Tiny achieving the highest Average Precision (AP) of 95.53% for horse detection and 89.12% for motorcycle detection. We observe that data augmentation significantly improves minority class detection, particularly benefiting deeper architectures. This study provides insights into architecture selection for imbalanced binary classification tasks and quantifies the impact of data augmentation strategies in mitigating class imbalance issues in object detection. |
| title | Comparative Study of CNN Architectures for Binary Classification of Horses and Motorcycles in the VOC 2008 Dataset |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.04344 |