Vegetables play an important role in people’s daily diet. However, vegetables often have many diseases that can affect consumers’ health. This study leverages the power of deep convolutional neural networks, specifically EfficientNet, in disease detection. Our study shows that EfficientNet has the potential to outperform previous studies with VGG19 and ResNet50 for diseases such as bacterial spot rot, black rot, and downy mildew. These promising results strengthen confidence in the progress of smart agriculture and its potential to improve disease detection in vegetables.