Self-supervised learning (SSL) approaches have shown promising capabilities in learning the representation from unlabeled data. Amongst them, momentum-based frameworks have attracted significant attention. Despite being a great success, these momentum-based SSL frameworks suffer from a large gap in representation between the online encoder (student) and the momentum encoder (teacher), which hinders performance on downstream tasks. This paper is the first to investigate and identify this invisible gap as a bottleneck that has been overlooked in the existing SSL frameworks, potentially preventing the models from learning good representation. To solve this problem, we propose "residual momentum" to directly reduce this gap to encourage the student to learn the representation as close to that of the teacher as possible, narrow the performance gap with the teacher, and significantly improve the existing SSL. Our method is straightforward, easy to implement, and can be easily plugged into other SSL frameworks. Extensive experimental results on numerous benchmark datasets and diverse network architectures have demonstrated the effectiveness of our method over the state-of-the-art contrastive learning baselines.
翻译:自我监督的学习(SSL)方法在从未贴标签的数据中学习代表性方面显示出很有希望的能力,其中,基于动力的框架引起了极大关注。尽管取得了巨大成功,但这些基于动力的SSL框架在在线编码器(学生)和动力编码器(教师)之间的代表性差距很大,这妨碍了下游任务的执行。本文是第一个调查和查明这一无形差距为现有SSL框架中忽视的瓶颈,有可能妨碍模型学习良好的代表性。为了解决这一问题,我们建议“剩余动力”直接缩小这一差距,鼓励学生尽可能接近教师的代表权,缩小教师的绩效差距,并大大改进现有的SSL。我们的方法简单易行,易于执行,并且很容易被插入其他SSL框架。许多基准数据集和不同网络结构的广泛实验结果表明我们的方法在最先进的对比学习基线上的有效性。