arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.02451cs.CV
收藏

面向对比学习的自适应数据增强

Adaptive Data Augmentation for Contrastive Learning

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)

Yuhan Zhang, He Zhu, Shan Yu

AI总结:

针对对比学习中固定数据增强难以适应网络演化的问题,本文提出 AdDA,利用闭环实时反馈自适应调整增强组合,以极小开销提升表征泛化性,并在 ImageNet-100 上验证有效。

摘要:

在计算机视觉中,对比学习是最先进的无监督学习框架。然而,以往大多数方法只是简单地应用固定组合的数据增强来提高数据效率,却忽视了其最优设置在训练过程中的变化。因此,增强操作的预定参数无法在整个训练期间始终很好地适应不断演化的网络,从而降低所学表征的质量。在本工作中,我们提出 AdDA,它为通用对比学习网络实现了一种闭环反馈结构。AdDA 的工作方式是允许网络根据实时反馈自适应地调整增强组合。这种在线调整有助于维持动态最优组合,并使网络能够以极小的计算开销获得更具泛化性的表征。在 ImageNet-100 分类的常用线性协议下,AdDA 取得了具有竞争力的结果(在 MoCo v2 上提升 +1.11%)。

英文摘要:

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).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑