论文标题
I-MIX：对比表示学习的域 - 不足的策略
i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
论文作者
论文摘要
对比表示学习已证明可以从未标记的数据中学习表示形式有效。但是，在依靠使用域知识精心设计的数据增强的视觉领域取得了很多进展。在这项工作中，我们提出了I-Mix，这是一种简单而有效的领域敏锐的正则化策略，用于改善对比度表示学习。我们将对比度学习作为培训非参数分类器，通过为批处理中的每个数据分配唯一的虚拟类，以培训非参数分类器。然后，在输入和虚拟标签空间中混合了数据实例，在培训过程中提供了更多增强的数据。在实验中，我们证明i-MIX始终提高跨领域（包括图像，语音和表格数据）的学会表示形式的质量。此外，我们通过跨模型和数据集大小的大量消融研究确认其正则化效果。该代码可在https://github.com/kibok90/imix上找到。
Contrastive representation learning has shown to be effective to learn representations from unlabeled data. However, much progress has been made in vision domains relying on data augmentations carefully designed using domain knowledge. In this work, we propose i-Mix, a simple yet effective domain-agnostic regularization strategy for improving contrastive representation learning. We cast contrastive learning as training a non-parametric classifier by assigning a unique virtual class to each data in a batch. Then, data instances are mixed in both the input and virtual label spaces, providing more augmented data during training. In experiments, we demonstrate that i-Mix consistently improves the quality of learned representations across domains, including image, speech, and tabular data. Furthermore, we confirm its regularization effect via extensive ablation studies across model and dataset sizes. The code is available at https://github.com/kibok90/imix.
