论文标题
多项式用于有效的视觉表示学习，以进行自我监督的预训练
Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-training
论文作者
论文摘要
近年来，已经研究了自我监督的学习，以应对可用标签数据的限制。在自我监督学习的主要组成部分中，数据增强管道是增强结果性能的关键因素之一。但是，大多数研究人员手动设计了增强管道，并且有限的转换收集可能会导致学习特征表示的鲁棒性。在这项工作中，我们提出了用于自我监督的代表学习（MA-SSRL）的多项式，该研究完全搜索了各种增强策略，以构建整个管道，以提高学识渊博的特征表示的鲁棒性。 MA-SSRL成功地学习了不变的功能表示，并提出了一种有效，有效且适应性的数据增强管道，以对不同的分布和域数据集进行自我监督的预训练。 MA-SSRL的表现优于先前有关转移和半监督基准测试的最新方法，同时需要更少的培训时代。
In recent years, self-supervised learning has been studied to deal with the limitation of available labeled-dataset. Among the major components of self-supervised learning, the data augmentation pipeline is one key factor in enhancing the resulting performance. However, most researchers manually designed the augmentation pipeline, and the limited collections of transformation may cause the lack of robustness of the learned feature representation. In this work, we proposed Multi-Augmentations for Self-Supervised Representation Learning (MA-SSRL), which fully searched for various augmentation policies to build the entire pipeline to improve the robustness of the learned feature representation. MA-SSRL successfully learns the invariant feature representation and presents an efficient, effective, and adaptable data augmentation pipeline for self-supervised pre-training on different distribution and domain datasets. MA-SSRL outperforms the previous state-of-the-art methods on transfer and semi-supervised benchmarks while requiring fewer training epochs.
