Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning
This addresses the practical limitation in label noise correction methods that require clean validation sets, making it more applicable for real-world noisy datasets.
The paper tackles the problem of learning from noisy labels by proposing a noisy meta label correction framework called STCT, which eliminates the need for extra clean validation data and achieves 96.9% label correction and 95.2% classification performance on CIFAR-10 with 80% symmetric noise, surpassing state-of-the-art methods.
Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets. Meta learning based label correction methods have demonstrated remarkable performance in LNL by designing various meta label rectification tasks. However, extra clean validation set is a prerequisite for these methods to perform label correction, requiring extra labor and greatly limiting their practicality. To tackle this issue, we propose a novel noisy meta label correction framework STCT, which counterintuitively uses noisy data to correct label noise, borrowing the spirit in the saying ``Set a Thief to Catch a Thief''. The core idea of STCT is to leverage noisy data which is i.i.d. with the training data as a validation set to evaluate model performance and perform label correction in a meta learning framework, eliminating the need for extra clean data. By decoupling the complex bi-level optimization in meta learning into representation learning and label correction, STCT is solved through an alternating training strategy between noisy meta correction and semi-supervised representation learning. Extensive experiments on synthetic and real-world datasets demonstrate the outstanding performance of STCT, particularly in high noise rate scenarios. STCT achieves 96.9% label correction and 95.2% classification performance on CIFAR-10 with 80% symmetric noise, significantly surpassing the current state-of-the-art.