Contrastive learning often relies on comparing positive anchor samples with multiple negative samples to perform Self-Supervised Learning (SSL). However, non-contrastive approaches like BYOL, SimSiam, and Barlow Twins achieve SSL without explicit negative samples. In this paper, we introduce a unified matrix information-theoretic framework that explains many contrastive and non-contrastive learning methods. We then propose a novel method Matrix-SSL based on matrix information theory. Experimental results reveal that Matrix-SSL significantly outperforms state-of-the-art methods on the ImageNet dataset under linear evaluation settings and on MS-COCO for transfer learning tasks. Specifically, when performing 100 epochs pre-training, our method outperforms SimCLR by 4.6%, and when performing transfer learning tasks on MS-COCO, our method outperforms previous SOTA methods such as MoCo v2 and BYOL up to 3.3% with only 400 epochs compared to 800 epochs pre-training. Code available at https://github.com/yifanzhang-pro/Matrix-SSL.

翻译：对比学习通常依赖将正锚定样本与多个负样本进行比较以进行自监督学习（SSL）。然而，非对比方法如BYOL、SimSiam和Barlow Twins无需显式负样本即可实现SSL。本文引入了一个统一的矩阵信息理论框架，该框架能够解释许多对比与非对比学习方法。基于矩阵信息理论，我们进一步提出了一种名为Matrix-SSL的新方法。实验结果表明，在线性评估设置下对ImageNet数据集，以及在迁移学习任务中对MS-COCO数据集，Matrix-SSL显著优于现有最先进方法。具体而言，在进行100个epoch预训练时，我们的方法比SimCLR高出4.6%；在MS-COCO上进行迁移学习任务时，使用仅400个epoch的预训练，我们的方法相比之前的SOTA方法（如MoCo v2和BYOL）性能提升高达3.3%，而后者需800个epoch。代码可在https://github.com/yifanzhang-pro/Matrix-SSL获取。