论文标题
转移和边缘化：用特权信息解释标签噪声
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
论文作者
论文摘要
监督的学习数据集通常具有特权信息，以培训时间可用但在测试时间无法使用的功能形式。提供标签的注释者的ID。我们认为特权信息对于解释标签噪声很有用，从而减少了嘈杂标签的有害影响。我们开发了一种简单有效的方法，用于通过神经网络进行监督学习：它通过与特权信息共享知识的权重转移，并在测试时大约在特权信息上进行边缘化。我们的方法，电车（转移和边缘化），其开销时间很少，并且具有与不使用特权信息相同的测试时间成本。 Tram在CIFAR-10H，Imagenet和Civil Imprive Benchmarks上表现出色。
Supervised learning datasets often have privileged information, in the form of features which are available at training time but are not available at test time e.g. the ID of the annotator that provided the label. We argue that privileged information is useful for explaining away label noise, thereby reducing the harmful impact of noisy labels. We develop a simple and efficient method for supervised learning with neural networks: it transfers via weight sharing the knowledge learned with privileged information and approximately marginalizes over privileged information at test time. Our method, TRAM (TRansfer and Marginalize), has minimal training time overhead and has the same test-time cost as not using privileged information. TRAM performs strongly on CIFAR-10H, ImageNet and Civil Comments benchmarks.
