Abstract
Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images, which has not been widely applied in self-supervised learning. This method is designed to provide better guidance for the model to understand underlying information, resulting in more useful representations. The proposed method is evaluated using contrastive learning, a widely used self-supervised learning method that has shown solid performance in downstream tasks. The results demonstrate the effectiveness of the proposed augmentation technique in improving the performance of self-supervised models.
Abstract (translated)
自监督学习近年来变得越来越流行,因为它能够在没有数据标注的情况下学习有意义的表示。本文提出了一种 novel 的图像增强技术,即重叠图像,这在自监督学习中并不广泛应用。该方法旨在为模型提供更好的指导,理解底层信息,从而生成更有用的表示。本文采用对比学习来评估该方法,这是一种广泛应用的自监督学习方法,在后续任务中表现出良好的性能。结果证明,该增强技术可以有效地提高自监督模型的性能。
URL
https://arxiv.org/abs/2301.09299
