A Novel Technique for Robust Training of Deep Networks With Multisource Weak Labeled Remote Sensing Data
This addresses the challenge of high-cost labeling in remote sensing by enabling effective use of unreliable data sources, though it is incremental as it builds on existing weak supervision methods.
The paper tackles the problem of training deep networks for remote sensing image classification with limited reliable labels by combining multiple weak label sources and a small reliable dataset, using transition matrices to weigh labels during training, achieving robust performance across different datasets.
Deep learning has gained broad interest in remote sensing image scene classification thanks to the effectiveness of deep neural networks in extracting the semantics from complex data. However, deep networks require large amounts of training samples to obtain good generalization capabilities and are sensitive to errors in the training labels. This is a problem in remote sensing since highly reliable labels can be obtained at high costs and in limited amount. However, many sources of less reliable labeled data are available, e.g., obsolete digital maps. In order to train deep networks with larger datasets, we propose both the combination of single or multiple weak sources of labeled data with a small but reliable dataset to generate multisource labeled datasets and a novel training strategy where the reliability of each source is taken in consideration. This is done by exploiting the transition matrices describing the statistics of the errors of each source. The transition matrices are embedded into the labels and used during the training process to weigh each label according to the related source. The proposed method acts as a weighting scheme at gradient level, where each instance contributes with different weights to the optimization of different classes. The effectiveness of the proposed method is validated by experiments on different datasets. The results proved the robustness and capability of leveraging on unreliable source of labels of the proposed method.