This paper presents the results of the evaluation of five deep learning architectures for the classification of soybean pest images. The performance of Inception-v3, Resnet-50, VGG-16, VGG-19 and Xception was evaluated for different fine-tuning and transfer learning strategies over a dataset of 5,000 images captured in real field conditions. The experimental results showed that the deep learning architectures trained with a fine-tuning can lead to higher classification rates in comparison to other approaches, reaching accuracies of up to 93.82%. In addition, deep learning architectures outperformed traditional feature extraction methods, such as SIFT and SURF with Bag-of-Visual Words approach, the semi-supervised learning method OPFSEMImst, and supervised learning methods used to classify images, for example, SVM, k-NN and Random Forest. The results indicate that architectures evaluated can support specialists and farmers in the pest control management in soybean fields.