A Novel Technique for Robust Training of Deep Networks With Multisource Weak Labeled Remote Sensing Data

Abstract

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.

16 pages, 9 figures, accepted article

References in corpus (4)

• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities
• Hyperspectral Image Classification in the Presence of Noisy Labels
• An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images

Cited by in corpus (4)

• SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images
• A class-driven hierarchical ResNet for classification of multispectral remote sensing images
• A deep multiple instance learning approach based on coarse labels for high-resolution land-cover mapping
• Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classification