2022/02/27 by Chen Gong, Gong, Chen, Bin, Kong +8
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning and Data Classification #Music and Audio Processing
paper · pdf · doi:10.48550/arxiv.2202.13472
openalex publication_date 2022/02/27 · openalex created_date 2022/08/20 · openalex updated_date 2026/07/28
Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we propose a robust label correction framework combining the ideas of small loss selection and noise correction, which learns network parameters and reassigns ground truth labels iteratively. Taking the expertise of DNNs to learn meaningful patterns before fitting noise, our framework first trains two networks over the current dataset with small loss selection. Based on the classification loss and agreement loss of two networks, we can measure the confidence of training data. More and more confident samples are selected for label correction during the learning process. We demonstrate our method on both synthetic and real-world datasets with different noise types and rates, including CIFAR-10, CIFAR-100 and Clothing1M, where our method outperforms the baseline approaches.