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，现有方法大多简单应用固定的数据增强组合来提升数据效率，忽略了最优设置在训练过程中的动态变化。因此，预定的增强操作参数在整个训练周期内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方法，该方法为通用对比学习网络引入了闭环反馈结构。AdDA通过允许网络根据实时反馈自适应调整增强组合来实现这一目标。这种在线调整有助于维持动态最优组合，并使网络以最小的计算开销获得更具泛化性的表征。在ImageNet-100分类任务的通用线性评估协议下，AdDA在MoCo v2基础上取得了具有竞争力的结果（提升1.11%）。