论文标题
MOPRO:动量原型哭泣的学习
MoPro: Webly Supervised Learning with Momentum Prototypes
论文作者
论文摘要
我们提出了一种不受监督学习的注释不可估量的注释,也不遭受自我监督学习的无法计算的性能,该方法不会受到注释。大多数现有关于Webly Syperifed代表性学习的作品都采用了一种香草监督学习方法,而没有考虑培训数据中普遍的噪音,而标签噪声的大多数先前学习方法对于现实世界中的大型嘈杂数据的有效性较小。我们提出了动量原型(MOPRO),这是一种简单的对比学习方法,可实现在线标签噪声校正,删除分布样本和表示学习。 MOPRO在网络视频中实现了最先进的性能,这是一个弱标记的嘈杂数据集。当验证的模型转移到下游图像分类和检测任务时,MOPRO还显示出卓越的性能。它的表现优于Imagenet在VOC上进行的1-SHOT分类的Imagenet监督预验证的模型,并且在1 \%的Imagenet标记样品中进行了填充时,优于+17.3最好的自我监督预定的模型。此外,莫普罗对分布变化更为强大。代码和预估计的模型可从https://github.com/salesforce/mopro获得。
We propose a webly-supervised representation learning method that does not suffer from the annotation unscalability of supervised learning, nor the computation unscalability of self-supervised learning. Most existing works on webly-supervised representation learning adopt a vanilla supervised learning method without accounting for the prevalent noise in the training data, whereas most prior methods in learning with label noise are less effective for real-world large-scale noisy data. We propose momentum prototypes (MoPro), a simple contrastive learning method that achieves online label noise correction, out-of-distribution sample removal, and representation learning. MoPro achieves state-of-the-art performance on WebVision, a weakly-labeled noisy dataset. MoPro also shows superior performance when the pretrained model is transferred to down-stream image classification and detection tasks. It outperforms the ImageNet supervised pretrained model by +10.5 on 1-shot classification on VOC, and outperforms the best self-supervised pretrained model by +17.3 when finetuned on 1\% of ImageNet labeled samples. Furthermore, MoPro is more robust to distribution shifts. Code and pretrained models are available at https://github.com/salesforce/MoPro.