arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.13872cs.CV
收藏

使用噪声标签进行学习的变换一致性

Transform consistency for learning with noisy labels

Beijing Jiaotong University(北京交通大学)

Rumeng Yi, Yaping Huang

摘要:

区分错误标记的样本对于处理噪声标签至关重要。以前的方法,如协同教学和JoCoR,引入了两个不同的网络,从嘈杂的样本中选择干净的样本,并只使用这些干净的样本来训练深度模型。与需要同时训练两个网络的方法不同,我们提出了一种简单有效的方法,只需使用一个单一的网络来识别干净的样本。我们发现,干净的样本更喜欢达到一致的预测,为原始图像和变换后的图像,而嘈杂的样本通常遭受不一致的预测。基于这一观察结果,我们引入了约束原图像和变换后图像之间的变换一致性来进行网络训练,然后选择损失小的样本来更新网络参数。此外,为了减轻噪声标签的负面影响,我们设计了一个分类损失,通过使用离线的硬标签和在线的软标签,以提供更可靠的监督,训练一个强大的模型。我们在CIFAR-10、CIFAR-100和Clothing 1 M数据集上进行了综合实验。与基线相比,我们达到了最先进的性能。特别是,在大多数情况下,我们提出的方法优于基线的大幅度。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑