Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
This addresses the challenge of noisy labels in deep learning, which is critical for real-world applications where data annotation is error-prone, representing a novel paradigm rather than an incremental improvement.
The paper tackles the problem of training deep neural networks with extremely noisy labels by proposing Co-teaching, a method where two networks teach each other to select clean data, resulting in superior robustness compared to state-of-the-art methods on noisy versions of MNIST, CIFAR-10, and CIFAR-100.
Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects of deep neural networks show that they would first memorize training data of clean labels and then those of noisy labels. Therefore in this paper, we propose a new deep learning paradigm called Co-teaching for combating with noisy labels. Namely, we train two deep neural networks simultaneously, and let them teach each other given every mini-batch: firstly, each network feeds forward all data and selects some data of possibly clean labels; secondly, two networks communicate with each other what data in this mini-batch should be used for training; finally, each network back propagates the data selected by its peer network and updates itself. Empirical results on noisy versions of MNIST, CIFAR-10 and CIFAR-100 demonstrate that Co-teaching is much superior to the state-of-the-art methods in the robustness of trained deep models.