Momentum Contrast for Unsupervised Visual Representation Learning
Kaiming He Haoqi Fan Yuxin Wu Saining Xie Ross Girshick Facebook AI Research (FAIR)
Abstract
We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning [29] as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.
中文速览
无监督视觉表征学习长期落后于有监督方法，核心难点在于如何在连续高维的图像空间里构建一个又大又一致的"负样本字典"供对比学习使用。MoCo（动量对比学习）用一个队列来维护这个字典——当前批次的编码结果入队、最旧的出队，使字典大小与批次大小彻底解耦；同时用动量更新（Momentum Update）让负样本的编码器缓慢演变，保证队列里所有键的表示始终由近似相同的编码器产生，从而兼顾"大"与"一致"两个目标。实验表明，MoCo在ImageNet线性分类协议下达到有竞争力的水平，更重要的是迁移能力极强，在PASCAL VOC、COCO等数据集的7项检测和分割任务中全面超越有监督预训练基线，部分任务领先幅度相当显著。这一结果意味着无监督与有监督视觉表征学习之间的鸿沟已被大幅弥合，MoCo有望成为众多视觉任务中ImageNet有监督预训练的实用替代方案。
原文 arXiv:1911.05722;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1911.05722v3