论文标题
通过认识混乱来概括
Generalization by Recognizing Confusion
论文作者
论文摘要
一种最近提供的称为“自适应训练”的技术通过允许它们即时调整训练标签，以避免过度适合可能被错误标记或以其他方式代表性的样品，以增强现代神经网络。通过将自适应目标与混合物相结合，我们进一步提高了自适应模型以识别图像的准确性。由此产生的分类器获得了用标签噪声损坏的数据集上的最新精度。标记噪声的鲁棒性意味着较低的概括差距；因此，我们的方法还导致了提高的普遍性。我们发现证据表明，这些算法的Rademacher复杂性很低，这表明对这种类型的深度学习模型的可证明概括是一种新的途径。最后，我们重点介绍了解决罕见类别的困难与噪声下的鲁棒性之间的新联系，因为在某种意义上，稀有类别与标签噪声没有区别。我们的代码可以在https://github.com/tuxianeer/generalizationConfusion上找到。
A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By combining the self-adaptive objective with mixup, we further improve the accuracy of self-adaptive models for image recognition; the resulting classifier obtains state-of-the-art accuracies on datasets corrupted with label noise. Robustness to label noise implies a lower generalization gap; thus, our approach also leads to improved generalizability. We find evidence that the Rademacher complexity of these algorithms is low, suggesting a new path towards provable generalization for this type of deep learning model. Last, we highlight a novel connection between difficulties accounting for rare classes and robustness under noise, as rare classes are in a sense indistinguishable from label noise. Our code can be found at https://github.com/Tuxianeer/generalizationconfusion.
