Contrastive learning demonstrates great promise for representation learning. Data augmentations play a critical role in contrastive learning by providing informative views of the data without needing the labels. However, the performance of the existing works heavily relies on the quality of the employed data augmentation (DA) functions, which are typically hand picked from a restricted set of choices. While exploiting a diverse set of data augmentations is appealing, the intricacies of DAs and representation learning may lead to performance degradation. To address this challenge and allow for a systemic use of large numbers of data augmentations, this paper proposes Contrastive Learning with Consistent Representations (CoCor). At the core of CoCor is a new consistency measure, DA consistency, which dictates the mapping of augmented input data to the representation space such that these instances are mapped to optimal locations in a way consistent to the intensity of the DA applied. Furthermore, a data-driven approach is proposed to learn the optimal mapping locations as a function of DA while maintaining a desired monotonic property with respect to DA intensity. The proposed techniques give rise to a semi-supervised learning framework based on bi-level optimization, achieving new state-of-the-art results for image recognition.

翻译：对比学习在表征学习中展现了巨大潜力。数据增强在对比学习中发挥着关键作用，它通过提供数据的信息化视图而无需标签信息。然而，现有工作的性能在很大程度上依赖于所采用数据增强（DA）函数的质量，这些函数通常是从有限的选择集中手工挑选的。虽然利用多样化的数据增强集合颇具吸引力，但DA的复杂性及表征学习可能导致性能下降。为解决这一挑战并实现大量数据增强的系统化使用，本文提出了一致性表征对比学习（CoCor）。CoCor的核心是一种新的一致性度量——DA一致性，其指导增强后的输入数据在表征空间的映射，使得这些实例被映射到最优位置，且映射方式与所应用DA的强度保持一致。此外，本文提出了一种数据驱动方法，学习作为DA函数的最优映射位置，同时保持与DA强度相关的所需单调性质。所提技术构建了一个基于双层优化的半监督学习框架，在图像识别任务中取得了新的最优结果。