Consistency-Regularized Learning for Remote Sensing Scene Classification With Noisy Labels
Ruizhe Hu, Zuoyong Li, Tao Wang, Rong Hu, George Papageorgiou, Guanghai Liu
Abstract
Recently, deep convolutional neural networks (DCNNs) have been widely adopted in scene classification for remote sensing (RS) images, yielding impressive results. One important assumption for training these models is that the image labels are free from errors. However, the mislabeling of certain images can severely degrade the performance of DCNN models. While existing methods offer some degree of mitigation, their effectiveness diminishes significantly in the presence of highly contaminated labels. This letter seeks to address this issue by proposing a robust scene classification model designed to learn from noisy labels. First, a semi-supervised approach is proposed, involving bootstrapping a model that uses a cleaned training set through coarse screening of potentially noisy labels. In particular, the model is trained using consistency regularization to enhance its robustness. Second, the remaining images with uncertain labels are further used to increase the number of images available for training. Here, dynamic thresholding is applied to detect and correct label errors. Lastly, the images and their labels from the two steps above are jointly used for final training. The proposed method is evaluated on three widely used RS datasets (AID, WHU-RS19, and UCMerced). The results demonstrate that the proposed approach outperforms competing methods, highlighting its efficacy in addressing label noise in RS datasets.