Momentum Contrast for Unsupervised Visual Representation Learning

作者：Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross B. Girshick · 发表于：Computer Vision and Pattern Recognition · 年份：2019 · DOI：10.1109/cvpr42600.2020.00975 · 被引用次数：15724 · 研究领域：Computer Science

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning 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.