Self-supervised learning has emerged as an increasingly popular research topic within the field of computer vision. In this study. we propose a novel self-supervised learning approach based on Mixup features as pretext tasks. The proposed method aims to learn visual representations by predicting the Mixup-Feature of a masked image. https://www.spidertattooz.com/Gruvi-Golden-Lager-Non-Alcoholic-6PKC-12-OZ/