IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 2020 · 58 citations · 65 references
ComputingComputer ScienceComputer VisionMachine LearningRemote SensingDeep LearningMulti-task LearningObject DetectionScene UnderstandingSemantic SegmentationAuxiliary Task LearningBoundary DetectionBoundary-aware SegmentationConvolutional Neural NetworksHeight EstimationMulti-task Deep LearningMultitask LearningRegularized Loss
Semantic segmentation and height estimation play fundamental roles in the scene understanding of remote sensing images with their wide variety of aerial applications. Recently, deep convolutional neural networks (DCNNs) have achieved state-of-the-art performance in both tasks. However, DCNN-based methods learn to accumulate contextual information over large receptive fields while lose the local detailed information, resulting in blurry object boundaries. The complicated ground object distribution and low interclass variance further aggravate the difficulty in generating accurate predictions. To address the above-mentioned issues, we propose a novel boundary-aware multitask learning (BAMTL) framework to perform three tasks, semantic segmentation, height estimation, and boundary detection, within a unified model. The boundary detection is employed as an auxiliary task to regularize the other two master tasks at both the feature space and output space. We present a boundary attentive module to build the cross-task interaction for master tasks, which enforce the networks to filter out the confident area and focus on learning the high-frequency details. We then introduce a boundary regularized loss term to further refine the prediction maps to be locally consistent while preserving boundary structures. With these formulations, our model improves the performance of both segmentation and height tasks, especially along the boundaries. Experimental results on two publicly available remote sensing datasets demonstrate that the proposed approach performs favorably against the state-of-the-art methods.
65
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations
Kaiming He, Georgia Gkioxari, Piotr Dollár et al. · 2017 · 28.8K citations
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · 22.1K citations
Hengshuang Zhao, Jianping Shi, Xiaojuan Qi et al. · 2017 · 15.5K citations