Comparative Study of CNN Architectures for Binary Classification of Horses and Motorcycles in the VOC 2008 Dataset

TL;DR

This study evaluates nine CNN architectures for binary classification of horses and motorcycles in VOC 2008, highlighting the impact of data augmentation and architecture choice on performance in imbalanced datasets.

Contribution

It provides a comprehensive comparison of modern CNN architectures and demonstrates the effectiveness of data augmentation in improving minority class detection.

Findings

ConvNeXt-Tiny achieves highest AP scores for both classes.

Data augmentation significantly enhances minority class detection.

Deeper architectures benefit more from data augmentation.

Abstract

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.