It is crucial to distinguish mislabeled samples for dealing with noisy labels. Previous methods such as Coteaching and JoCoR introduce two different networks to select clean samples out of the noisy ones and only use these clean ones to train the deep models. Different from these methods which require to train two networks simultaneously, we propose a simple and effective method to identify clean samples only using one single network. We discover that the clean samples prefer to reach consistent predictions for the original images and the transformed images while noisy samples usually suffer from inconsistent predictions. Motivated by this observation, we introduce to constrain the transform consistency between the original images and the transformed images for network training, and then select small-loss samples to update the parameters of the network. Furthermore, in order to mitigate the negative influence of noisy labels, we design a classification loss by using the off-line hard labels and on-line soft labels to provide more reliable supervisions for training a robust model. We conduct comprehensive experiments on CIFAR-10, CIFAR-100 and Clothing1M datasets. Compared with the baselines, we achieve the state-of-the-art performance. Especially, in most cases, our proposed method outperforms the baselines by a large margin.
翻译:区分标签错误的样本对于处理吵闹的标签至关重要。 以前的方法,如Coteaching和JoCorR, 引入了两个不同的网络,从吵闹的标签中挑选干净的样本,而只使用这些干净的样本来培训深层模型。不同的方法是,同时培训两个网络,我们建议了一种简单有效的方法,只用一个网络来识别干净的样本。我们发现,干净的样本更愿意对原始图像和变形图像作出一致的预测,而噪音的样本通常会受到不一致的预测。根据这一观察,我们引入了限制原始图像和改造后的网络培训图像之间转变的一致性,然后选择了小损失样本来更新网络的参数。此外,为了减轻噪音标签的负面影响,我们设计了一种分类损失分类方法,使用离线硬标签和在线软标签来提供更可靠的监督,以培训一个强健的模型。我们在CFAR-10、CIFAR-100和Slade1M数据集上进行了全面实验。与基线相比,我们实现了最先进的模型。特别是以大基线来分析。