Given the time-intensive nature of manual fundus examination and its significant dependence on expert knowledge, the task of computer-aided multi-classification of diabetic retinopathy (DR) severity is of crucial importance. However, the application of multi-classification for DR severity remains limited by a scarcity of high-quality training data, despite its potential. Moreover, challenges such as suboptimal data quality, ambiguous pathological characteristics, and minimal dissimilarity among categories are prevalent. Further research on image preprocessing methods is necessary. This study proposes a new framework for diabetic retinopathy classification, PMADR-Net (Progressive Multiscale Attention Network for Diabetic Retinopathy). By applying progressive multiscale training and attention mechanisms, this framework is suitable for few-shot medical image classification. It could automatically shift its focus towards learning samples of pathological features that are more challenging to discriminate. Moreover, in order to mitigate the class imbalance in the dataset, this research employs a balanced sampling approach and a patch reconstruction technique to produce multiscale features, thereby facilitating the model’s accurate differentiation of each category. Our proposed model achieved a classification accuracy of 93.97% and an AUC evaluation metric of 0.9850, demonstrating its superior effectiveness over state-of-the-art techniques and showing potential for widespread application in similar medical classification tasks involving small datasets.