Comparison of MobileNetV3-Small and EfficientNetV2-Small for Low-Resolution X-ray Image Classification

Abstract

Lung diseases are a global health concern that require accurate and efficient automated diagnostic systems, particularly in healthcare facilities with limited resources. This study evaluates the performance and computational efficiency of two lightweight convolutional neural network architectures, namely MobileNetV3-Small and EfficientNetV2-Small, on the multi-label classification task of low-resolution ChestMNIST chest X-ray images. Experiments were conducted across eight testing scenarios with and without light spatial data augmentation. The evaluation encompassed predictive performance using accuracy and Area Under the Curve (AUC-ROC) metrics, as well as computational efficiency based on the number of parameters, FLOPs, model size, training time, and inference time. Results indicated that although both models achieved high accuracy (0.93–0.95), MobileNetV3-Small consistently produced higher and more stable AUC-ROC values compared to EfficientNetV2-Small, while being significantly more computationally efficient. Moreover, the application of light spatial data augmentation on low-resolution datasets such as ChestMNIST did not provide consistent performance improvements and instead increased training costs, indicating the limited effectiveness of simple geometric variations when spatial information in the images is highly constrained. These findings provide insight that, in low-resolution medical image multi-label classification, the suitability of an efficient CNN architecture design has a greater impact on overall performance than increasing model complexity or applying light spatial augmentation.