Exponential moving average of vision transformers for skin lesion classification [Deri lezyonu sınıflandırması için görüntü dönüştürücülerinin üstel hareketli ortalaması]

Official URL: https://dx.doi.org/10.1109/SIU71813.2026.11637046

Skin lesion classification is a critical medical image analysis task in which early diagnosis significantly improves survival rates. In this work, we address the parameter variability problem of Vision Transformer based models arising from small batch sizes at the end of training. We propose maintaining an auxiliary model that tracks the Exponential Moving Average (EMA) of the online model parameters during training. The proposed approach smooths parameter fluctuations and improves training stability without introducing any additional computational overhead. Experiments on the ISIC 2019 dataset demonstrate that, in addition to reducing parameter variability, the EMA model consistently achieves higher Macro-F1 scores (6.93%) and accuracy rates (2.67%) compared to the online model.