论文标题
快速MOCO：与组合斑块的增强基于动量的对比学习
Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches
论文作者
论文摘要
近年来，基于对比的自我监督学习方法取得了巨大的成功。但是，自学要求非常长的训练时代（例如，MoCo V3的800个时代）才能获得有希望的结果，这对于一般学术界来说是不可接受的，并阻碍了该主题的发展。这项工作重新审视了基于动量的对比学习框架，并确定了两个增强观点仅产生一个积极对的效率低下。我们提出了快速MOCO-一个新颖的框架，该框架利用组合贴片从两个增强视图中构造了多对的多对，这提供了丰富的监督信号，这些信号带来了可忽视的额外计算成本。经过100个时期训练的快速MOCO实现了73.5％的线性评估准确性，类似于接受800个时期训练的Moco V3（Resnet-50骨干）。额外的训练（200个时期）进一步将结果提高到75.1％，这与最先进的方法相当。几个下游任务的实验也证实了快速MOCO的有效性。
Contrastive-based self-supervised learning methods achieved great success in recent years. However, self-supervision requires extremely long training epochs (e.g., 800 epochs for MoCo v3) to achieve promising results, which is unacceptable for the general academic community and hinders the development of this topic. This work revisits the momentum-based contrastive learning frameworks and identifies the inefficiency in which two augmented views generate only one positive pair. We propose Fast-MoCo - a novel framework that utilizes combinatorial patches to construct multiple positive pairs from two augmented views, which provides abundant supervision signals that bring significant acceleration with neglectable extra computational cost. Fast-MoCo trained with 100 epochs achieves 73.5% linear evaluation accuracy, similar to MoCo v3 (ResNet-50 backbone) trained with 800 epochs. Extra training (200 epochs) further improves the result to 75.1%, which is on par with state-of-the-art methods. Experiments on several downstream tasks also confirm the effectiveness of Fast-MoCo.
