It is extreme labor expensive to collect such pixel-wise annotated training data for semantic segmentation and object extraction for Remote Sensing images. We intend to develop weakly supervised learning techniques to address such challenge. Recently, we introduce a label noise-adaptive (NA) fully convolution neural network trained on noisy labeled data generated by GIS building footprint data.

Z. Zhang, W. Guo, M. Li and W. Yu, "GIS-Supervised Building Extraction With Label Noise-Adaptive Fully Convolutional Neural Network," in IEEE Geoscience and Remote Sensing Letters.

赵娟萍, 郭炜炜, 柳彬, 崔世勇, 张增辉, 郁文贤. 基于概率转移卷积神经网络的含噪标记SAR图像分类[J]. 雷达学报, 2017, 6(5): 514-523. doi: 10.12000/JR16140