Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner mitigate label noise? To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not. Through this transformation, the reduction of the noise rate is theoretically guaranteed, and hence it is in principle easier to handle noisy similarity labels. Amazingly, DNNs that predict the clean class labels can be trained from noisy data pairs if they are first pretrained from noisy data points. Class2Simi is computationally efficient because not only this transformation is on-the-fly in mini-batches, but also it just changes loss computation on top of model prediction into a pairwise manner. Its effectiveness is verified by extensive experiments.
翻译:使用吵闹标签的学习近年来引起了许多关注, 主流方法在主流方法中以简单方式进行。 同时, 双向方式在监督性标准学习和不受监督的对比性学习中显示出巨大的潜力。 因此, 自然提出的问题是: 是否以双向方式学习来减轻标签的噪音? 为了给出一个肯定的答案, 在本文中, 我们提出了一个称为 Sleg2Simi 的框架: 它将带有吵闹类标签的数据点转换成带有吵闹相似标签的数据对口, 在一个类似标签中, 类似标签表示一对夫妇是否分享类标签。 通过这种转变, 降低噪音率在理论上是有保障的, 因而原则上更容易处理吵闹的相似标签。 令人惊讶的是, 预测干净等级标签的DNNNs如果先是从吵闹的数据对口开始训练, 就可以从噪音数据对口中训练。 类2Simi 具有计算效率, 因为不仅这种转换在小型作战中是可飞的, 而且它只是将损失计算结果转换成一种配对式的。 它的有效性通过广泛的实验得到验证。