论文标题
改进自我监督学习的简单数据混合
A Simple Data Mixing Prior for Improving Self-Supervised Learning
论文作者
论文摘要
数据混合（例如混合，cutmix，resizemix）是推进识别模型的重要组成部分。在本文中，我们专注于研究其在自我监督环境中的有效性。 By noticing the mixed images that share the same source images are intrinsically related to each other, we hereby propose SDMP, short for $\textbf{S}$imple $\textbf{D}$ata $\textbf{M}$ixing $\textbf{P}$rior, to capture this straightforward yet essential prior, and position such mixed images as additional $\textbf{positive对} $促进自我监督的表示学习。我们的实验验证了所提出的SDMP可以使数据混合有助于一组自学的学习框架（例如MoCo）实现了更好的准确性和分布范围的鲁棒性。更值得注意的是，我们的SDMP是成功利用数据混合以改善（而不是伤害）视觉变压器在自我监督的环境中的性能的第一种方法。代码可在https://github.com/oliverrensu/sdmp上公开获取
Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images that share the same source images are intrinsically related to each other, we hereby propose SDMP, short for $\textbf{S}$imple $\textbf{D}$ata $\textbf{M}$ixing $\textbf{P}$rior, to capture this straightforward yet essential prior, and position such mixed images as additional $\textbf{positive pairs}$ to facilitate self-supervised representation learning. Our experiments verify that the proposed SDMP enables data mixing to help a set of self-supervised learning frameworks (e.g., MoCo) achieve better accuracy and out-of-distribution robustness. More notably, our SDMP is the first method that successfully leverages data mixing to improve (rather than hurt) the performance of Vision Transformers in the self-supervised setting. Code is publicly available at https://github.com/OliverRensu/SDMP
