用动态字典实现大规模无监督视觉表征学习，效果逼近有监督方法。
Momentum Contrast for Unsupervised Visual Representation Learning
- 构建带队列和动量编码器的动态字典，支持在线扩展与一致性维护。
- 在ImageNet上线性分类性能达91.7%，在多个检测分割任务上超越有监督预训练。
- 适合追求高效无监督表征、无需标注数据的研究者与工程师。
我们提出动量对比（Momentum Contrast, MoCo）用于无监督视觉表征学习。从对比学习即字典查询的角度出发，MoCo 构建了一个带有队列和动量平均编码器的动态字典，能够在运行时持续构建大且一致的字典，从而促进对比式无监督学习。MoCo 在 ImageNet 分类任务中采用常见线性协议取得了具有竞争力的结果，准确率达到 91.7%。更重要的是，其学习到的表示可有效迁移到下游任务，在 PASCAL VOC、COCO 等数据集上的 7 个检测与分割任务中表现优于对应的有监督预训练模型，部分任务差距显著。这表明在许多视觉任务中，无监督与有监督表征学习之间的差距已基本弥合。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。