Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literature (with several recent exceptions) of learning with noisy labels focuses on the case when the label noise is independent of features. Practically, annotations errors tend to be instance-dependent and often depend on the difficulty levels of recognizing a certain task. Applying existing results from instance-independent settings would require a significant amount of estimation of noise rates. Therefore, providing theoretically rigorous solutions for learning with instance-dependent label noise remains a challenge. In this paper, we propose CORES$^{2}$ (COnfidence REgularized Sample Sieve), which progressively sieves out corrupted examples. The implementation of CORES$^{2}$ does not require specifying noise rates and yet we are able to provide theoretical guarantees of CORES$^{2}$ in filtering out the corrupted examples. This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting. We demonstrate the performance of CORES$^{2}$ on CIFAR10 and CIFAR100 datasets with synthetic instance-dependent label noise and Clothing1M with real-world human noise. As of independent interests, our sample sieve provides a generic machinery for anatomizing noisy datasets and provides a flexible interface for various robust training techniques to further improve the performance. Code is available at https://github.com/UCSC-REAL/cores.
翻译:带有人文注释的标签往往容易引起噪音,因此,这种噪音的存在将降低由此形成的深神经网络(DNN)模型的性能。许多文献(除了最近的一些例外)与吵闹标签学习的文献(除了最近的一些例外)都集中在标签噪音独立于特性之外的情况下。实际上,说明错误往往依赖实例,往往取决于确认某一任务的困难程度。应用依赖实例的环境的现有结果需要大量估计噪音率。因此,在理论上为学习基于实例的标签噪音提供严格的解决方案仍然是一项挑战。在本文中,我们提议用CORES$%%2}(COnficulalizized样板Sieve)学习的很多文献(CoRES$%2}(最近的一些例外情况除外)集中在标签噪音不受特性影响的情况下。执行CORES$%2}(实际错误错误)往往取决于确认某一任务的难度。但在过滤腐败实例时,我们能够提供理论性保证。这种高品质的样本精准性能让我们在培训DNNU(DN2)解决方案时分别处理一些腐败的例子。这种分解的样本(COficialalation Regialalalation Supply sex sex) ex) exexexalalalalalal sholviewalation shes 和Crealation sholview shes 。我们展示了真实性能在Crealxxxxxx 和CIRlationslationalxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx 。我们展示了真实性能、CIR 和CIRxxxxxxxxxxxxxxxxxxxxx