In computer vision, contrastive learning is the most advanced unsupervised learning framework. Yet most previous methods simply apply fixed composition of data augmentations to improve data efficiency, which ignores the changes in their optimal settings over training. Thus, the pre-determined parameters of augmentation operations cannot always fit well with an evolving network during the whole training period, which degrades the quality of the learned representations. In this work, we propose AdDA, which implements a closed-loop feedback structure to a generic contrastive learning network. AdDA works by allowing the network to adaptively adjust the augmentation compositions according to the real-time feedback. This online adjustment helps maintain the dynamic optimal composition and enables the network to acquire more generalizable representations with minimal computational overhead. AdDA achieves competitive results under the common linear protocol on ImageNet-100 classification (+1.11% on MoCo v2).

翻译：在计算机视觉领域，对比学习是最先进的无监督学习框架。然而，以往大多数方法仅应用固定的数据增强组合来提升数据效率，忽略了其最优设定在训练过程中的变化。因此，预定的增强操作参数在整个训练期间无法始终与不断演化的网络良好适配，从而降低了所学表征的质量。本文提出AdDA，该方法为通用对比学习网络实现了闭环反馈结构。AdDA通过允许网络根据实时反馈自适应调整增强组合来发挥作用。这种在线调整有助于维持动态最优组合，使网络能够在最小化计算开销的同时获取更具泛化能力的表征。在ImageNet-100分类任务的标准线性评估协议下，AdDA取得了具有竞争力的结果（在MoCo v2上提升+1.11%）。