Revisiting Interpolation for Noisy Label Correction
Yuanzhuo Xu, Xiaoguang Niu, Jie Yang, Ruiyi Su, Jian Zhang, Shubo Liu, Steve Drew
Abstract
Label correction methods are popular for their simple architecture in learning with noisy labels. However, they suffer severely from false label correction and achieve subpar performance compared with state-of-the-art methods. In this paper, we revisit the label correction methods through theoretical analysis of gradient scaling and demonstrate that the sample-wise dynamic and class-wise uniformity of interpolation weight prevents memorization of the mislabeled samples. We then propose DULC, a simple yet effective label correction method that uses the normalized Jensen-Shannon divergence (JSD) metric as the interpolation weight to promote sample-wise dynamic and class-wise uniformity. Additionally, we provide theoretical evidence that sharpening predictions in label correction facilitates the memorization of true class, and we achieve it by employing the augmentation strategy along with the sharpening function. Extensive experiments on CIFAR-10, CIFAR-100, TinyImageNet, WebVision and Clothing1M datasets demonstrate substantial improvements over state-of-the-art methods.
BibTeX
@article{Xu_Niu_Yang_Su_Zhang_Liu_Drew_2025, title={Revisiting Interpolation for Noisy Label Correction}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35489}, DOI={10.1609/aaai.v39i20.35489}, abstractNote={Label correction methods are popular for their simple architecture in learning with noisy labels. However, they suffer severely from false label correction and achieve subpar performance compared with state-of-the-art methods. In this paper, we revisit the label correction methods through theoretical analysis of gradient scaling and demonstrate that the sample-wise dynamic and class-wise uniformity of interpolation weight prevents memorization of the mislabeled samples. We then propose DULC, a simple yet effective label correction method that uses the normalized Jensen-Shannon divergence (JSD) metric as the interpolation weight to promote sample-wise dynamic and class-wise uniformity. Additionally, we provide theoretical evidence that sharpening predictions in label correction facilitates the memorization of true class, and we achieve it by employing the augmentation strategy along with the sharpening function. Extensive experiments on CIFAR-10, CIFAR-100, TinyImageNet, WebVision and Clothing1M datasets demonstrate substantial improvements over state-of-the-art methods.}, number={20}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Xu, Yuanzhuo and Niu, Xiaoguang and Yang, Jie and Su, Ruiyi and Zhang, Jian and Liu, Shubo and Drew, Steve}, year={2025}, month={Apr.}, pages={21833-21841} }