high performance computing on graphics processing units: hgpu.org

Precisely-labeled data sets with sufficient amount of samples are notably important for training deep convolutional neural networks (CNNs). However, many of the available real-world data sets contain erroneously labeled samples and the error in labels of training sample makes it a daunting task to learn a well-performing deep CNN model. In this work, we consider the problem of training a deep CNN model for image classification with mislabeled training samples – an issue that is common in real image data sets with tags supplied by amateur users. To solve this problem, we propose an auxiliary image regularization technique, which automatically exploits the mutual context information among training images and encourages the model to select reliable images to robustify the learning process. Comprehensive experiments on benchmark data sets clearly demonstrate our proposed regularized CNN model is resistant to label noise in training data.